welcome this obligatory slide so yeah
welcome this obligatory slide so yeah ask questions through the app and rate
ask questions through the app and rate
ask questions through the app and rate the session thank you
the session thank you
the session thank you we’re gonna talk about just machine
we’re gonna talk about just machine
we’re gonna talk about just machine learning and your first steps into the
learning and your first steps into the
learning and your first steps into the world of machine so if you already
world of machine so if you already
world of machine so if you already involve the machine learning you might
involve the machine learning you might
involve the machine learning you might as well leave because everything I’m
as well leave because everything I’m
as well leave because everything I’m telling you you already know so my name
telling you you already know so my name
telling you you already know so my name is Dave still I’m developer for kwinto
is Dave still I’m developer for kwinto
is Dave still I’m developer for kwinto kwinto is an agile consultancy agency
kwinto is an agile consultancy agency
kwinto is an agile consultancy agency which specializes in dotnet in Java you
which specializes in dotnet in Java you
which specializes in dotnet in Java you can have Twitter me at my handle yeah
can have Twitter me at my handle yeah
can have Twitter me at my handle yeah I’m a father of one little AI and
I’m a father of one little AI and
I’m a father of one little AI and another one is on its way soon so today
another one is on its way soon so today
another one is on its way soon so today we’re going to talk about intelligence
we’re going to talk about intelligence
we’re going to talk about intelligence artificial challenges machine learning
artificial challenges machine learning
artificial challenges machine learning how does relate to each other what
how does relate to each other what
how does relate to each other what methods are used in this area how
methods are used in this area how
methods are used in this area how machine learning is applied in everyday
machine learning is applied in everyday
machine learning is applied in everyday life section and how to get started so
life section and how to get started so
life section and how to get started so how to get yourself on your way
how to get yourself on your way
how to get yourself on your way eventually so intelligence artificial
eventually so intelligence artificial
eventually so intelligence artificial term is a machine learning let’s have a
term is a machine learning let’s have a
term is a machine learning let’s have a quick introduction machine learning yeah
quick introduction machine learning yeah
quick introduction machine learning yeah it sounds quite scary nobody really
it sounds quite scary nobody really
it sounds quite scary nobody really knows what it is but it is very popular
knows what it is but it is very popular
knows what it is but it is very popular in the media you see everywhere in
in the media you see everywhere in
in the media you see everywhere in articles in newspapers machine learning
articles in newspapers machine learning
articles in newspapers machine learning this machine learning that how do you
this machine learning that how do you
this machine learning that how do you teach a driverless car to drive etc etc
teach a driverless car to drive etc etc
teach a driverless car to drive etc etc and it’s also yeah you could find it on
and it’s also yeah you could find it on
and it’s also yeah you could find it on Netflix for example most of you probably
Netflix for example most of you probably
Netflix for example most of you probably already know but when you use a when a
already know but when you use a when a
already know but when you use a when a few movies like Arrested Development it
few movies like Arrested Development it
few movies like Arrested Development it usually gives a suggestion about well
usually gives a suggestion about well
usually gives a suggestion about well you’ve seen Arrested Development’s they
you’ve seen Arrested Development’s they
you’ve seen Arrested Development’s they must like Legally Blonde and Bob’s
must like Legally Blonde and Bob’s
must like Legally Blonde and Bob’s Burgers and some other movies it doesn’t
Burgers and some other movies it doesn’t
Burgers and some other movies it doesn’t just do these recommendations nearly
just do these recommendations nearly
just do these recommendations nearly really it does it’s based on well
really it does it’s based on well
really it does it’s based on well millions and millions of user inputs
millions and millions of user inputs
millions and millions of user inputs from other accounts and using machine
from other accounts and using machine
from other accounts and using machine learning to make these recommendations
learning to make these recommendations
learning to make these recommendations other way well in which it participates
other way well in which it participates
other way well in which it participates in real life is your mo
in real life is your mo
in real life is your mo everyone has one for example your Google
everyone has one for example your Google
everyone has one for example your Google assistants your katana your Alexa or
assistants your katana your Alexa or
assistants your katana your Alexa or your Siri they’re all basically smart
your Siri they’re all basically smart
your Siri they’re all basically smart digital assistants which are capable of
digital assistants which are capable of
digital assistants which are capable of voice recognitions and capable of
voice recognitions and capable of
voice recognitions and capable of parsing simple questions for example who
parsing simple questions for example who
parsing simple questions for example who played James Bond in quantum solace
played James Bond in quantum solace
played James Bond in quantum solace it’s capable of answering that it’s
it’s capable of answering that it’s
it’s capable of answering that it’s Daniel crack but it was also capable of
Daniel crack but it was also capable of
Daniel crack but it was also capable of answering is what other movies did he
answering is what other movies did he
answering is what other movies did he play however this is a quite a more
play however this is a quite a more
play however this is a quite a more complex question for simple fact that it
complex question for simple fact that it
complex question for simple fact that it requires context for he refers to
requires context for he refers to
requires context for he refers to previous results so it needs to know
previous results so it needs to know
previous results so it needs to know what the previous results for were
what the previous results for were
what the previous results for were before it can answer that question now
before it can answer that question now
before it can answer that question now nowadays those digital agents are quite
nowadays those digital agents are quite
nowadays those digital agents are quite capable of answering those questions and
capable of answering those questions and
capable of answering those questions and also this is because of a copious amount
also this is because of a copious amount
also this is because of a copious amount of machine learning intelligence what is
of machine learning intelligence what is
of machine learning intelligence what is intelligence
intelligence
intelligence well most of you guys know this but it’s
well most of you guys know this but it’s
well most of you guys know this but it’s basically the capability of reasoning
basically the capability of reasoning
basically the capability of reasoning and solving problems artificial
and solving problems artificial
and solving problems artificial intelligence is simulating this through
intelligence is simulating this through
intelligence is simulating this through computers so a computer who’s capable of
computers so a computer who’s capable of
computers so a computer who’s capable of reasoning and solving problems it’s a
reasoning and solving problems it’s a
reasoning and solving problems it’s a big problem main and it’s divided in
big problem main and it’s divided in
big problem main and it’s divided in several actually quite a few super mice
several actually quite a few super mice
several actually quite a few super mice these are four of these just a subset
these are four of these just a subset
these are four of these just a subset for example natural language processing
for example natural language processing
for example natural language processing that’s the ability that you’re capable
that’s the ability that you’re capable
that’s the ability that you’re capable of processing natural language by a
of processing natural language by a
of processing natural language by a computer and it’s capable of
computer and it’s capable of
computer and it’s capable of interpreting exactly what you say
interpreting exactly what you say
interpreting exactly what you say knowledge representation would be the
knowledge representation would be the
knowledge representation would be the problem main where you have to have a
problem main where you have to have a
problem main where you have to have a computer resemble internally the
computer resemble internally the
computer resemble internally the knowledge of a certain problem may for
knowledge of a certain problem may for
knowledge of a certain problem may for example medical assistance it would have
example medical assistance it would have
example medical assistance it would have to have a model internally from which
to have a model internally from which
to have a model internally from which you can deduce solutions and problems
you can deduce solutions and problems
you can deduce solutions and problems automated reasoning that means that
automated reasoning that means that
automated reasoning that means that you’re capable of coming up with new
you’re capable of coming up with new
you’re capable of coming up with new solutions or written solutions for
solutions or written solutions for
solutions or written solutions for example for puzzles and also for comedy
example for puzzles and also for comedy
example for puzzles and also for comedy questions for example if you’re at home
questions for example if you’re at home
questions for example if you’re at home at work and Google of course know says
at work and Google of course know says
at work and Google of course know says Google knows where you are and he notice
Google knows where you are and he notice
Google knows where you are and he notice also there’s a Wi-Fi at home is in use
also there’s a Wi-Fi at home is in use
also there’s a Wi-Fi at home is in use well Google should be able to do 2d
well Google should be able to do 2d
well Google should be able to do 2d views well oh that is not supposed to
views well oh that is not supposed to
views well oh that is not supposed to happen yes not at home
happen yes not at home
happen yes not at home so it should be able to alert you and
so it should be able to alert you and
so it should be able to alert you and inform you about these things but what
inform you about these things but what
inform you about these things but what we’re gonna concentrate about on today
we’re gonna concentrate about on today
we’re gonna concentrate about on today it’s machine learning machine learning
it’s machine learning machine learning
it’s machine learning machine learning is the area where actually a machine is
is the area where actually a machine is
is the area where actually a machine is capable of forming his own solutions to
capable of forming his own solutions to
capable of forming his own solutions to problems a short history of machine
problems a short history of machine
problems a short history of machine learning will be to start with the
learning will be to start with the
learning will be to start with the Turing test the Turing test was devised
Turing test the Turing test was devised
Turing test the Turing test was devised by Alan Turing in 1950 and capable
by Alan Turing in 1950 and capable
by Alan Turing in 1950 and capable it’s basically where there’s an operator
it’s basically where there’s an operator
it’s basically where there’s an operator sitting behind the screen and conversing
sitting behind the screen and conversing
sitting behind the screen and conversing actually with someone on the other side
actually with someone on the other side
actually with someone on the other side or screen and on the other side should
or screen and on the other side should
or screen and on the other side should be a computer or a human and the idea is
be a computer or a human and the idea is
be a computer or a human and the idea is that the computer should be able to fool
that the computer should be able to fool
that the computer should be able to fool the human into believing that he is a
the human into believing that he is a
the human into believing that he is a computer if he’s capable of doing that
computer if he’s capable of doing that
computer if he’s capable of doing that then each part smart enough actually to
then each part smart enough actually to
then each part smart enough actually to be called intelligent and well our
be called intelligent and well our
be called intelligent and well our touring would that’s what I’m doing of
touring would that’s what I’m doing of
touring would that’s what I’m doing of course a computer would deserve to be
course a computer would deserve to be
course a computer would deserve to be called intelligent if could deceive a
called intelligent if could deceive a
called intelligent if could deceive a human into believing there was human Oh
human into believing there was human Oh
human into believing there was human Oh 1952 we already had the first a I
1952 we already had the first a I
1952 we already had the first a I application actually our to assemble
application actually our to assemble
application actually our to assemble implemented the game engine actually AI
implemented the game engine actually AI
implemented the game engine actually AI which was capable of playing checkers
which was capable of playing checkers
which was capable of playing checkers using thousands of rheticus register
using thousands of rheticus register
using thousands of rheticus register checker games and having the application
checker games and having the application
checker games and having the application learn from those games
learn from those games
learn from those games well fast-forward five 45 years to the
well fast-forward five 45 years to the
well fast-forward five 45 years to the future or actually almost 20 years in
future or actually almost 20 years in
future or actually almost 20 years in the past 1997 IBM deep blue defeated
the past 1997 IBM deep blue defeated
the past 1997 IBM deep blue defeated Kasparov it was a big thing back then at
Kasparov it was a big thing back then at
Kasparov it was a big thing back then at the time it was fought okay we made big
the time it was fought okay we made big
the time it was fought okay we made big progress but for example the game of Go
progress but for example the game of Go
progress but for example the game of Go which is much higher complexity it’s way
which is much higher complexity it’s way
which is much higher complexity it’s way way in the future decades well there was
way in the future decades well there was
way in the future decades well there was another big breakthrough actually in
another big breakthrough actually in
another big breakthrough actually in 2011 IBM Watson was capable after
2011 IBM Watson was capable after
2011 IBM Watson was capable after defeating his opponents in jeopardy
defeating his opponents in jeopardy
defeating his opponents in jeopardy jeopardy is basically a game quiz an
jeopardy is basically a game quiz an
jeopardy is basically a game quiz an answer is given and a contestant has to
answer is given and a contestant has to
answer is given and a contestant has to give the question that longs to that
give the question that longs to that
give the question that longs to that answer and the difficulty is you have to
answer and the difficulty is you have to
answer and the difficulty is you have to actually first know the context you have
actually first know the context you have
actually first know the context you have to be able to formulate correct
to be able to formulate correct
to be able to formulate correct sentences so all adjectives nouns
sentences so all adjectives nouns
sentences so all adjectives nouns pronouns conjugations do you have to be
pronouns conjugations do you have to be
pronouns conjugations do you have to be correct oh yeah I need to know what
correct oh yeah I need to know what
correct oh yeah I need to know what you’re talking about
you’re talking about
you’re talking about so it was an impressive feat however
so it was an impressive feat however
so it was an impressive feat however even then go was still a long way well
even then go was still a long way well
even then go was still a long way well actually it wasn’t in 2016 most of you
actually it wasn’t in 2016 most of you
actually it wasn’t in 2016 most of you know google deepmind defeated go go
know google deepmind defeated go go
know google deepmind defeated go go champion lee sedol
champion lee sedol
champion lee sedol and actually did so four times against
and actually did so four times against
and actually did so four times against one and actually now they already
one and actually now they already
one and actually now they already retired it but basically there was a
retired it but basically there was a
retired it but basically there was a breakthrough because in 2015 their
breakthrough because in 2015 their
breakthrough because in 2015 their father would still be decades away so
father would still be decades away so
father would still be decades away so it’s like having a flying car being able
it’s like having a flying car being able
it’s like having a flying car being able for pre-order tomorrow it’s really
for pre-order tomorrow it’s really
for pre-order tomorrow it’s really impressive how fast I went well there
impressive how fast I went well there
impressive how fast I went well there was short introduction about history
was short introduction about history
was short introduction about history what kind of intelligence do we have we
what kind of intelligence do we have we
what kind of intelligence do we have we have considered weak AI a strong AI
have considered weak AI a strong AI
have considered weak AI a strong AI strong AI usually means that you have
strong AI usually means that you have
strong AI usually means that you have artificial generic
artificial generic
artificial generic basically that means you have artificial
basically that means you have artificial
basically that means you have artificial intelligence as a human level you’re
intelligence as a human level you’re
intelligence as a human level you’re capable of reasoning of several problems
capable of reasoning of several problems
capable of reasoning of several problems domains and you’re not stuck on only
domains and you’re not stuck on only
domains and you’re not stuck on only checkers for example we on the other end
checkers for example we on the other end
checkers for example we on the other end is really really specific it means that
is really really specific it means that
is really really specific it means that the AI is basically of capable
the AI is basically of capable
the AI is basically of capable performing one task for example checkers
performing one task for example checkers
performing one task for example checkers or chess in this game so as we saw in
or chess in this game so as we saw in
or chess in this game so as we saw in the history of AI there was suddenly a
the history of AI there was suddenly a
the history of AI there was suddenly a big progress first was 45 years then
big progress first was 45 years then
big progress first was 45 years then suddenly without within 17 years or
suddenly without within 17 years or
suddenly without within 17 years or everything changed how was this possible
everything changed how was this possible
everything changed how was this possible well the first thing will be big data
well the first thing will be big data
well the first thing will be big data we’ve now such copious amounts of data
we’ve now such copious amounts of data
we’ve now such copious amounts of data that were capable of actually training
that were capable of actually training
that were capable of actually training these algorithms that we want to use for
these algorithms that we want to use for
these algorithms that we want to use for AI this was actually in 1997 really
AI this was actually in 1997 really
AI this was actually in 1997 really unimaginable that there will be Google
unimaginable that there will be Google
unimaginable that there will be Google which is warehouses and warehouses and
which is warehouses and warehouses and
which is warehouses and warehouses and warehouses of computers storing data
warehouses of computers storing data
warehouses of computers storing data with cat pictures I don’t know and we
with cat pictures I don’t know and we
with cat pictures I don’t know and we have big computer this basically means
have big computer this basically means
have big computer this basically means that we have also large large data
that we have also large large data
that we have also large large data centers of computing power cheap and
centers of computing power cheap and
centers of computing power cheap and specialized another one less known fact
specialized another one less known fact
specialized another one less known fact actually still advancing algorithms
actually still advancing algorithms
actually still advancing algorithms actually
so what’s it transmitting algorithms to
so what’s it transmitting algorithms to that when I studied in 1999 neural
that when I studied in 1999 neural
that when I studied in 1999 neural networks were basically well nice but
networks were basically well nice but
networks were basically well nice but not really feasible due to the fact that
not really feasible due to the fact that
not really feasible due to the fact that it was slow it took a lot of computing
it was slow it took a lot of computing
it was slow it took a lot of computing power and time to train such a model
power and time to train such a model
power and time to train such a model however in 2006 there was this person
however in 2006 there was this person
however in 2006 there was this person whose name I forgot sorry who actually
whose name I forgot sorry who actually
whose name I forgot sorry who actually revolutionize a part of the training
revolutionize a part of the training
revolutionize a part of the training mechanism in neural networking making it
mechanism in neural networking making it
mechanism in neural networking making it possible actually to use neural
possible actually to use neural
possible actually to use neural networking in 2010 this already was
networking in 2010 this already was
networking in 2010 this already was redundant but it gave a new boost to
redundant but it gave a new boost to
redundant but it gave a new boost to neural networks and making it possible
neural networks and making it possible
neural networks and making it possible to actually use these the other one is
to actually use these the other one is
to actually use these the other one is the fact that there are several
the fact that there are several
the fact that there are several companies now heavily invested in
companies now heavily invested in
companies now heavily invested in machine learning throwing big money
machine learning throwing big money
machine learning throwing big money against it and really really putting
against it and really really putting
against it and really really putting time and effort in it so these factors
time and effort in it so these factors
time and effort in it so these factors combined is why AI is out of seven so
combined is why AI is out of seven so
combined is why AI is out of seven so let’s just say the past seven years
let’s just say the past seven years
let’s just say the past seven years making a really really strong return
making a really really strong return
making a really really strong return machine learning how does machine
machine learning how does machine
machine learning how does machine learning differ from normal programming
learning differ from normal programming
learning differ from normal programming most you know but basically machine
most you know but basically machine
most you know but basically machine learning it means that in regular
learning it means that in regular
learning it means that in regular programming year data if you program if
programming year data if you program if
programming year data if you program if they eat into computer you get output
they eat into computer you get output
they eat into computer you get output basic machine learning it’s a little bit
basic machine learning it’s a little bit
basic machine learning it’s a little bit different of course you have data give
different of course you have data give
different of course you have data give it a certain output that you expect for
it a certain output that you expect for
it a certain output that you expect for the data and the computer supposed to
the data and the computer supposed to
the data and the computer supposed to produce a program that would solve that
produce a program that would solve that
produce a program that would solve that problem for you so you’re not actually
problem for you so you’re not actually
problem for you so you’re not actually doing everything by itself for example
doing everything by itself for example
doing everything by itself for example well we have an apple FF orangish you
well we have an apple FF orangish you
well we have an apple FF orangish you can’t really compare apples and oranges
can’t really compare apples and oranges
can’t really compare apples and oranges but that’s right how would you
but that’s right how would you
but that’s right how would you differentiate these well first of all I
differentiate these well first of all I
differentiate these well first of all I I would think caller so well what if
I would think caller so well what if
I would think caller so well what if it’s a grayscale image you would try
it’s a grayscale image you would try
it’s a grayscale image you would try texture
texture
texture well if you add bananas well it would
well if you add bananas well it would
well if you add bananas well it would have to add another exclusion another
have to add another exclusion another
have to add another exclusion another exception etc etc try a French
exception etc etc try a French
exception etc etc try a French eventually you get a whole bunch of code
eventually you get a whole bunch of code
eventually you get a whole bunch of code which is actually I’m maintainable it
which is actually I’m maintainable it
which is actually I’m maintainable it will never be actually fully covering
will never be actually fully covering
will never be actually fully covering all areas of fruit so this is where
all areas of fruit so this is where
all areas of fruit so this is where machine learning comes in yeah you train
machine learning comes in yeah you train
machine learning comes in yeah you train it and it will come up with the answer
it and it will come up with the answer
it and it will come up with the answer program itself so what matters of
program itself so what matters of
program itself so what matters of machine learning you have where
machine learning you have where
machine learning you have where supervised learning with unsupervised
supervised learning with unsupervised
supervised learning with unsupervised learning ever
learning ever
learning ever we have reinforcement learning
we have reinforcement learning
we have reinforcement learning semi-supervised learning is basically a
semi-supervised learning is basically a
semi-supervised learning is basically a 1/2 a solution between supervised
1/2 a solution between supervised
1/2 a solution between supervised learning and unsupervised learning we
learning and unsupervised learning we
learning and unsupervised learning we will discuss each of these in the
will discuss each of these in the
will discuss each of these in the conversation flight supervised learning
conversation flight supervised learning
conversation flight supervised learning so what supervised learning supervised
so what supervised learning supervised
so what supervised learning supervised learning means that you have a machine
learning means that you have a machine
learning means that you have a machine learning algorithm which you feed input
learning algorithm which you feed input
learning algorithm which you feed input and keep training it down at the input
and keep training it down at the input
and keep training it down at the input each time you give input it will give a
each time you give input it will give a
each time you give input it will give a prediction and then you tell it whether
prediction and then you tell it whether
prediction and then you tell it whether the prediction of the label for example
the prediction of the label for example
the prediction of the label for example is right or wrong based if it’s wrong it
is right or wrong based if it’s wrong it
is right or wrong based if it’s wrong it was just this model I keep repeating
was just this model I keep repeating
was just this model I keep repeating keep repeating it until the error is low
keep repeating it until the error is low
keep repeating it until the error is low eventually well you extract the
eventually well you extract the
eventually well you extract the classifier model from that machine
classifier model from that machine
classifier model from that machine learning algorithm because that’s what’s
learning algorithm because that’s what’s
learning algorithm because that’s what’s all about it put it in your program and
all about it put it in your program and
all about it put it in your program and use it you give the input it will give a
use it you give the input it will give a
use it you give the input it will give a prediction so what the main algorithms
prediction so what the main algorithms
prediction so what the main algorithms used what it’s used for for supervised
used what it’s used for for supervised
used what it’s used for for supervised learning classification and regression
learning classification and regression
learning classification and regression classification actually means that let’s
classification actually means that let’s
classification actually means that let’s say you have two features feature is
say you have two features feature is
say you have two features feature is actually the best aspects of an input on
actually the best aspects of an input on
actually the best aspects of an input on which you want to train the model so
which you want to train the model so
which you want to train the model so feature 152 and it tries to classify
feature 152 and it tries to classify
feature 152 and it tries to classify each one
each one
each one and for regression is usually you have a
and for regression is usually you have a
and for regression is usually you have a feature so I have value is an output
feature so I have value is an output
feature so I have value is an output anyone to have it estimate which value
anyone to have it estimate which value
anyone to have it estimate which value it might occur if you give it an input
it might occur if you give it an input
it might occur if you give it an input to clarify this for classification for
to clarify this for classification for
to clarify this for classification for example we have a data set of houses and
example we have a data set of houses and
example we have a data set of houses and we’re going to classify kind of train
we’re going to classify kind of train
we’re going to classify kind of train into a classification where is something
into a classification where is something
into a classification where is something the house is cheap or house is expensive
the house is cheap or house is expensive
the house is cheap or house is expensive so as input features we use living area
so as input features we use living area
so as input features we use living area you use price and give it the trip you
you use price and give it the trip you
you use price and give it the trip you keep training keep training and each
keep training keep training and each
keep training keep training and each time it will tell it will give the house
time it will tell it will give the house
time it will tell it will give the house of saying it’s cheap it’s expensive we
of saying it’s cheap it’s expensive we
of saying it’s cheap it’s expensive we say now your fingers cheap but this
say now your fingers cheap but this
say now your fingers cheap but this experience it was justice model
experience it was justice model
experience it was justice model eventually we’ll have a model that can
eventually we’ll have a model that can
eventually we’ll have a model that can separate houses based on the living area
separate houses based on the living area
separate houses based on the living area and the price and determine yeah that’s
and the price and determine yeah that’s
and the price and determine yeah that’s cheap that’s expensive regression on our
cheap that’s expensive regression on our
cheap that’s expensive regression on our hand works a little different let’s say
hand works a little different let’s say
hand works a little different let’s say we have the living area yes and the
we have the living area yes and the
we have the living area yes and the corresponding prices I will keep telling
corresponding prices I will keep telling
corresponding prices I will keep telling it just given the data what the idea is
it just given the data what the idea is
it just given the data what the idea is then eventually it will have a function
then eventually it will have a function
then eventually it will have a function that will actually match living area
that will actually match living area
that will actually match living area with with the price if and if the model
with with the price if and if the model
with with the price if and if the model we can give it just a living area and
we can give it just a living area and
we can give it just a living area and will produce a price for us an
will produce a price for us an
will produce a price for us an estimation of the expected price so
estimation of the expected price so
estimation of the expected price so assured classification would label it
assured classification would label it
assured classification would label it and a regression would try to estimate
and a regression would try to estimate
and a regression would try to estimate actual value if there are any questions
actual value if there are any questions
actual value if there are any questions do ask please well for this problem we
do ask please well for this problem we
do ask please well for this problem we use neural networks usually you can do
use neural networks usually you can do
use neural networks usually you can do it in other ways I’ve not seen it but
it in other ways I’ve not seen it but
it in other ways I’ve not seen it but you could and their network is based on
you could and their network is based on
you could and their network is based on the biological neuron it looks
the biological neuron it looks
the biological neuron it looks schematically like this inputs foreigner
schematically like this inputs foreigner
schematically like this inputs foreigner come through the dendrite so top left I
come through the dendrite so top left I
come through the dendrite so top left I will go for the necklace and
will go for the necklace and
will go for the necklace and it will give a signal based on the input
it will give a signal based on the input
it will give a signal based on the input food axon to the axon terminals quite
food axon to the axon terminals quite
food axon to the axon terminals quite basic in computer science you would
basic in computer science you would
basic in computer science you would model it like this basically these are
model it like this basically these are
model it like this basically these are all the inputs each input has certain
all the inputs each input has certain
all the inputs each input has certain weight so important it was some the
weight so important it was some the
weight so important it was some the weights times the input to make a
weights times the input to make a
weights times the input to make a summation of step and then it will
summation of step and then it will
summation of step and then it will determine whether or not it will output
determine whether or not it will output
determine whether or not it will output the signal and how strong that signal
the signal and how strong that signal
the signal and how strong that signal will be so that will be the activation
will be so that will be the activation
will be so that will be the activation function well combining all these
function well combining all these
function well combining all these networks you will get something like
networks you will get something like
networks you will get something like this this is a free layered neural
this this is a free layered neural
this this is a free layered neural network you get the input layer you have
network you get the input layer you have
network you get the input layer you have the output layer every hidden layer it’s
the output layer every hidden layer it’s
the output layer every hidden layer it’s called the hidden layer because nobody
called the hidden layer because nobody
called the hidden layer because nobody sees hidden layer you only see the input
sees hidden layer you only see the input
sees hidden layer you only see the input and output as a outside view and this is
and output as a outside view and this is
and output as a outside view and this is fully connected to network so each
fully connected to network so each
fully connected to network so each neuron is connected to each other never
to make this a little bit clearer I
to make this a little bit clearer I would like to demonstrate this x-ray
would like to demonstrate this x-ray
would like to demonstrate this x-ray through something called
tensorflow preyed playground all of you
tensorflow preyed playground all of you have already played with this or see a
have already played with this or see a
have already played with this or see a few hands well it’s really nice tool it
few hands well it’s really nice tool it
few hands well it’s really nice tool it gives you an idea about how neural
gives you an idea about how neural
gives you an idea about how neural networks work you play around with it
networks work you play around with it
networks work you play around with it I created a match for spiral here but
I created a match for spiral here but
I created a match for spiral here but let’s just it’s a very handy tool for
let’s just it’s a very handy tool for
let’s just it’s a very handy tool for visualizing so you can determine here
visualizing so you can determine here
visualizing so you can determine here whether it want to classify or regress
for this input we take the two
for this input we take the two coordinates of each point so X 1 X 2 so
coordinates of each point so X 1 X 2 so
coordinates of each point so X 1 X 2 so the x and y coordinate and we’re going
the x and y coordinate and we’re going
the x and y coordinate and we’re going to Train it well don’t have any hit
to Train it well don’t have any hit
to Train it well don’t have any hit liars there’s a nice separation we don’t
liars there’s a nice separation we don’t
liars there’s a nice separation we don’t need hidden edge for this so let’s make
need hidden edge for this so let’s make
need hidden edge for this so let’s make a little more complex
a little more complex
a little more complex that’s my so you have four groups
that’s my so you have four groups
that’s my so you have four groups basically she’s here
basically she’s here
basically she’s here orange is here blue is there and blues
orange is here blue is there and blues
orange is here blue is there and blues there let’s try to train it well it’s
there let’s try to train it well it’s
there let’s try to train it well it’s not gonna match is it so we add a hidden
not gonna match is it so we add a hidden
not gonna match is it so we add a hidden layer let’s see what it does you will
layer let’s see what it does you will
layer let’s see what it does you will see that suddenly is this nice color up
see that suddenly is this nice color up
see that suddenly is this nice color up basically the figure the line is the
basically the figure the line is the
basically the figure the line is the bigger the weight if it’s blue is
bigger the weight if it’s blue is
bigger the weight if it’s blue is positive if it’s orange is negative and
positive if it’s orange is negative and
positive if it’s orange is negative and these blue white deficiency is here on
these blue white deficiency is here on
these blue white deficiency is here on the neurons are basically the activation
the neurons are basically the activation
the neurons are basically the activation functions a representation of the
functions a representation of the
functions a representation of the activation function basically if you see
activation function basically if you see
activation function basically if you see blue here it means everything that comes
blue here it means everything that comes
blue here it means everything that comes in this area would be positive and the
in this area would be positive and the
in this area would be positive and the rest will be nil so this is not gonna
rest will be nil so this is not gonna
rest will be nil so this is not gonna work this separation so let’s add some
work this separation so let’s add some
work this separation so let’s add some extra and try it again
extra and try it again
extra and try it again so a few extra neurons and suddenly it’s
so a few extra neurons and suddenly it’s
so a few extra neurons and suddenly it’s capable of really dividing and
capable of really dividing and
capable of really dividing and classifying the output
so this is clear for everybody okay so
so this is clear for everybody okay so in deep learning deep learning actually
in deep learning deep learning actually
in deep learning deep learning actually means nothing more than that you use a
means nothing more than that you use a
means nothing more than that you use a neural network that is more than one lis
neural network that is more than one lis
neural network that is more than one lis hidden layer nothing else so this is
hidden layer nothing else so this is
hidden layer nothing else so this is deep ler deep neural network because
deep ler deep neural network because
deep ler deep neural network because that’s free hidden layer this is an
that’s free hidden layer this is an
that’s free hidden layer this is an example of how in short these layers
example of how in short these layers
example of how in short these layers would represent each activation method
would represent each activation method
would represent each activation method so let’s say you have an input layer
so let’s say you have an input layer
so let’s say you have an input layer which is a picture the cashman are
which is a picture the cashman are
which is a picture the cashman are categorized in cats and dogs will
categorized in cats and dogs will
categorized in cats and dogs will influence the human face and each for
influence the human face and each for
influence the human face and each for each pixel we input a nerve so let’s say
each pixel we input a nerve so let’s say
each pixel we input a nerve so let’s say there’s an 18 by 18 pixel top it off I
there’s an 18 by 18 pixel top it off I
there’s an 18 by 18 pixel top it off I wouldn’t know how much many notes it
wouldn’t know how much many notes it
wouldn’t know how much many notes it would be but plenty in the inner layer
would be but plenty in the inner layer
would be but plenty in the inner layer we get actually the edges first then
we get actually the edges first then
we get actually the edges first then later on you’ll see that it’s a
later on you’ll see that it’s a
later on you’ll see that it’s a combination of edges so the nose eyes
combination of edges so the nose eyes
combination of edges so the nose eyes after that in later life later you see
after that in later life later you see
after that in later life later you see the object models coming out a nice one
the object models coming out a nice one
the object models coming out a nice one would also be online you can also find
would also be online you can also find
would also be online you can also find the inception model the exception model
the inception model the exception model
the inception model the exception model is an efficient model trained
is an efficient model trained
is an efficient model trained pre-trained Fisher model from cool that
pre-trained Fisher model from cool that
pre-trained Fisher model from cool that they released this can just use play
they released this can just use play
they released this can just use play around with it’s quite complicated the
around with it’s quite complicated the
around with it’s quite complicated the model itself it’s this big and they also
model itself it’s this big and they also
model itself it’s this big and they also made a project someone it from Google
made a project someone it from Google
made a project someone it from Google inception which actually showed you
inception which actually showed you
inception which actually showed you shows actually all the layers and shows
shows actually all the layers and shows
shows actually all the layers and shows you how this would look as we just shown
you how this would look as we just shown
you how this would look as we just shown before on a real neural network so this
before on a real neural network so this
before on a real neural network so this would be on the first level the
would be on the first level the
would be on the first level the separators and if we look at the output
separators and if we look at the output
separators and if we look at the output after the first layer I don’t know where
after the first layer I don’t know where
after the first layer I don’t know where you can see but this is basically a heat
you can see but this is basically a heat
you can see but this is basically a heat map of what is highlighted of the dog
map of what is highlighted of the dog
map of what is highlighted of the dog that you saw previously
that you saw previously
that you saw previously with regard to the edges so you can see
with regard to the edges so you can see
with regard to the edges so you can see here be the shape of the dog here yeah
here be the shape of the dog here yeah
here be the shape of the dog here yeah it’s interesting to see I would suggest
it’s interesting to see I would suggest
it’s interesting to see I would suggest recommend what looking at by the way
recommend what looking at by the way
recommend what looking at by the way this is a Python notebook many of you
this is a Python notebook many of you
this is a Python notebook many of you probably have heard it in previous
probably have heard it in previous
probably have heard it in previous sessions about it I would really
sessions about it I would really
sessions about it I would really recommend using it because you maybe if
recommend using it because you maybe if
recommend using it because you maybe if you smart mark or something this is
you smart mark or something this is
you smart mark or something this is basically the same principle you can
basically the same principle you can
basically the same principle you can just write text put in code that you can
just write text put in code that you can
just write text put in code that you can reuse later it gets explained it gets
reuse later it gets explained it gets
reuse later it gets explained it gets shown and it’s executable continuing so
shown and it’s executable continuing so
shown and it’s executable continuing so there’s not just one neural network
there’s not just one neural network
there’s not just one neural network architecture there are quite a few this
architecture there are quite a few this
architecture there are quite a few this from the neural network is you and it
from the neural network is you and it
from the neural network is you and it shows well that you really have to
shows well that you really have to
shows well that you really have to consider what kind of architect you
consider what kind of architect you
consider what kind of architect you would decide upon if you want to build
would decide upon if you want to build
would decide upon if you want to build your own neural network so there are
your own neural network so there are
your own neural network so there are several frameworks that already provide
several frameworks that already provide
several frameworks that already provide trained models through an API train
trained models through an API train
trained models through an API train while some through an API is some don’t
while some through an API is some don’t
while some through an API is some don’t for example do Google Cloud machine
for example do Google Cloud machine
for example do Google Cloud machine learning engine the IBM Watson machine
learning engine the IBM Watson machine
learning engine the IBM Watson machine learning that’s fruit bluemix my
learning that’s fruit bluemix my
learning that’s fruit bluemix my crewmate machine learning recently apple
crewmate machine learning recently apple
crewmate machine learning recently apple also introduced around machine learning
also introduced around machine learning
also introduced around machine learning for in your applications cafeteria to
for in your applications cafeteria to
for in your applications cafeteria to has a whole model zoo which can download
has a whole model zoo which can download
has a whole model zoo which can download and use but for first for actually
and use but for first for actually
and use but for first for actually provide api city can directly using the
provide api city can directly using the
provide api city can directly using the application IBM watson was by the way a
application IBM watson was by the way a
application IBM watson was by the way a byproduct of IBM watson of course after
byproduct of IBM watson of course after
byproduct of IBM watson of course after day did the Jeopardy faying they had a
day did the Jeopardy faying they had a
day did the Jeopardy faying they had a very nice answer a question question
very nice answer a question question
very nice answer a question question answer mechanism but also learned a
answer mechanism but also learned a
answer mechanism but also learned a whole lot and gave the profiles of api
whole lot and gave the profiles of api
whole lot and gave the profiles of api for the public so like they have a
for the public so like they have a
for the public so like they have a fishing api Oh
fishing api Oh
fishing api Oh voice recognition API well the same goes
voice recognition API well the same goes
voice recognition API well the same goes for Google Cloud and all the others but
for Google Cloud and all the others but
for Google Cloud and all the others but it’s very nice you can play for example
it’s very nice you can play for example
it’s very nice you can play for example for google you can play around with the
for google you can play around with the
for google you can play around with the fishing api you can just well let’s just
fishing api you can just well let’s just
fishing api you can just well let’s just take my daughter for example it’s very
take my daughter for example it’s very
take my daughter for example it’s very nice so you can just
nice so you can just
nice so you can just upload it tip tip and will detect
upload it tip tip and will detect
upload it tip tip and will detect actually everything let’s show you it
actually everything let’s show you it
actually everything let’s show you it will say she’s neat I don’t have no idea
will say she’s neat I don’t have no idea
will say she’s neat I don’t have no idea what her emotions are not join the Sora
what her emotions are not join the Sora
what her emotions are not join the Sora no anger no surprised she’s like numb
no anger no surprised she’s like numb
no anger no surprised she’s like numb emotionless apparently yeah she is
emotionless apparently yeah she is
emotionless apparently yeah she is apparently a person infant child skin
apparently a person infant child skin
apparently a person infant child skin and for some reason Google thinks is day
and for some reason Google thinks is day
and for some reason Google thinks is day though most of you probably see it’s
though most of you probably see it’s
though most of you probably see it’s night inside lights on so it’s very nice
night inside lights on so it’s very nice
night inside lights on so it’s very nice you can just get an account for free
you can just get an account for free
you can just get an account for free it’s very fun to play with
it’s very fun to play with
it’s very fun to play with and you can just call through REST API
and you can just call through REST API
and you can just call through REST API from your programs
from your programs
from your programs alright that was supervised learning
alright that was supervised learning
alright that was supervised learning unsupervised learning there basically
unsupervised learning there basically
unsupervised learning there basically means the opposite of supervised
means the opposite of supervised
means the opposite of supervised learning of course what this mean is
learning of course what this mean is
learning of course what this mean is basically I have a bunch of data I’ve no
basically I have a bunch of data I’ve no
basically I have a bunch of data I’ve no idea how the structure it might be I
idea how the structure it might be I
idea how the structure it might be I have a machine learning algorithm I just
have a machine learning algorithm I just
have a machine learning algorithm I just give it to the algorithm and say ok you
give it to the algorithm and say ok you
give it to the algorithm and say ok you try to sort this out I’ll come back
try to sort this out I’ll come back
try to sort this out I’ll come back later and after you’ve done that you
later and after you’ve done that you
later and after you’ve done that you have a classifier model it can give
have a classifier model it can give
have a classifier model it can give input and we’ll give you more or less
input and we’ll give you more or less
input and we’ll give you more or less where he expects your input to belong to
where he expects your input to belong to
where he expects your input to belong to so they’re mainly free algorithms that
so they’re mainly free algorithms that
so they’re mainly free algorithms that are used for this clustering when you’ve
are used for this clustering when you’ve
are used for this clustering when you’ve tried to find similar instances so these
tried to find similar instances so these
tried to find similar instances so these are the instances these would be feature
are the instances these would be feature
are the instances these would be feature showed aspects that you put into it and
showed aspects that you put into it and
showed aspects that you put into it and here is she okay these free instances
here is she okay these free instances
here is she okay these free instances have the same features these belong to
have the same features these belong to
have the same features these belong to each other together anomaly detection
each other together anomaly detection
each other together anomaly detection well everything here would be white and
well everything here would be white and
well everything here would be white and there’s just one entry which is
there’s just one entry which is
there’s just one entry which is completely different than the rest
completely different than the rest
completely different than the rest Association discovery that’s and when
Association discovery that’s and when
Association discovery that’s and when you basically see okay for example these
you basically see okay for example these
you basically see okay for example these free instances have feature from the
free instances have feature from the
free instances have feature from the second column but they also have all
second column but they also have all
second column but they also have all features from the fourth column well an
features from the fourth column well an
features from the fourth column well an example from practice will be let’s say
example from practice will be let’s say
example from practice will be let’s say from food web shop and you notice
from food web shop and you notice
from food web shop and you notice everyone who buys
everyone who buys
everyone who buys buns and salad also seems to buy burgers
buns and salad also seems to buy burgers
buns and salad also seems to buy burgers there will be Association discovery so
there will be Association discovery so
there will be Association discovery so when someone buy sell it and buns yeah
when someone buy sell it and buns yeah
when someone buy sell it and buns yeah there might be some burgers in force for
there might be some burgers in force for
there might be some burgers in force for clustering by the way it’s means that
clustering by the way it’s means that
clustering by the way it’s means that you don’t change the data set or you
you don’t change the data set or you
you don’t change the data set or you don’t go grouping it but basically you
don’t go grouping it but basically you
don’t go grouping it but basically you try to find where the clusters are so
try to find where the clusters are so
try to find where the clusters are so this is basically an example k-means
this is basically an example k-means
this is basically an example k-means clustering means you have before you
clustering means you have before you
clustering means you have before you start you to say okay I want to find
start you to say okay I want to find
start you to say okay I want to find three clusters
three clusters
three clusters that’s the K free and I’m gonna start at
that’s the K free and I’m gonna start at
that’s the K free and I’m gonna start at random I just point here there and there
random I just point here there and there
random I just point here there and there and then we’re going to try to shift
and then we’re going to try to shift
and then we’re going to try to shift those mean points of the clusters the
those mean points of the clusters the
those mean points of the clusters the center points of the clusters until the
center points of the clusters until the
center points of the clusters until the distances of points become minimized and
distances of points become minimized and
distances of points become minimized and keep iterating that until there are no
keep iterating that until there are no
keep iterating that until there are no changes so keep shifting the mean points
changes so keep shifting the mean points
changes so keep shifting the mean points those are these tilt found the best
those are these tilt found the best
those are these tilt found the best solution for free clusters the downside
solution for free clusters the downside
solution for free clusters the downside is you would have to know that it’s free
is you would have to know that it’s free
is you would have to know that it’s free clusters in advance that’s a bit of the
clusters in advance that’s a bit of the
clusters in advance that’s a bit of the – well we also did it a quinta for too
– well we also did it a quinta for too
– well we also did it a quinta for too much we offer products products by
much we offer products products by
much we offer products products by customer profile so we also did
customer profile so we also did
customer profile so we also did clustering basic category manufacturer
clustering basic category manufacturer
clustering basic category manufacturer postal code and eventually we were
postal code and eventually we were
postal code and eventually we were capable of actually making product
capable of actually making product
capable of actually making product suggestions based on what they were
suggestions based on what they were
suggestions based on what they were searching for so for example there was a
searching for so for example there was a
searching for so for example there was a probability of 0 90 percent that product
probability of 0 90 percent that product
probability of 0 90 percent that product ID 11 807 which is SES plus drill set
ID 11 807 which is SES plus drill set
ID 11 807 which is SES plus drill set would should be recommended
so okay that was supervised learning
so okay that was supervised learning with unsupervised learning and now this
with unsupervised learning and now this
with unsupervised learning and now this reinforcement learning what is
reinforcement learning what is
reinforcement learning what is reinforcement learning that’s when you
reinforcement learning that’s when you
reinforcement learning that’s when you have an algorithm they can perform
have an algorithm they can perform
have an algorithm they can perform certain actions for example game you can
certain actions for example game you can
certain actions for example game you can go left
go left
go left you can’t go right maybe sure each
you can’t go right maybe sure each
you can’t go right maybe sure each action has an effect on the world and as
action has an effect on the world and as
action has an effect on the world and as a return you get a reward increasing
a return you get a reward increasing
a return you get a reward increasing score for example and get a new status
score for example and get a new status
score for example and get a new status you moved right you’re about that same
you moved right you’re about that same
you moved right you’re about that same position where you were before well a
position where you were before well a
position where you were before well a nice example is actually this game it’s
nice example is actually this game it’s
nice example is actually this game it’s a brick most of you know right break out
it’s an Atari game and it was actually
it’s an Atari game and it was actually used by deepmind before they get to
used by deepmind before they get to
used by deepmind before they get to train their models using reinforcement
train their models using reinforcement
train their models using reinforcement learning it’s also one of the reasons
learning it’s also one of the reasons
learning it’s also one of the reasons Google bottom like this so well awesome
Google bottom like this so well awesome
Google bottom like this so well awesome yeah ok so basically they just took two
yeah ok so basically they just took two
yeah ok so basically they just took two pics or social scream its input and
pics or social scream its input and
pics or social scream its input and score that’s all that was input for the
score that’s all that was input for the
score that’s all that was input for the model nothing else just the score and a
model nothing else just the score and a
model nothing else just the score and a pixels and he knew what what he had to
pixels and he knew what what he had to
pixels and he knew what what he had to do left or right but okay it starts
do left or right but okay it starts
do left or right but okay it starts training minutes of training
training minutes of training
training minutes of training Leslie sucks at it so you see man
Leslie sucks at it so you see man
Leslie sucks at it so you see man sometimes he does hit the ball by
sometimes he does hit the ball by
sometimes he does hit the ball by coincidence but yeah it’s not very very
coincidence but yeah it’s not very very
coincidence but yeah it’s not very very proficient but after two hours played
proficient but after two hours played
proficient but after two hours played like an expert so he had no problems so
like an expert so he had no problems so
like an expert so he had no problems so he’s pretty good I would have problems
he’s pretty good I would have problems
he’s pretty good I would have problems beating him
yeah the reward change is basically the
yeah the reward change is basically the model it’s based on this Markov decision
model it’s based on this Markov decision
model it’s based on this Markov decision process and I’ll get back to that in a
process and I’ll get back to that in a
process and I’ll get back to that in a second after two hours actually
second after two hours actually
second after two hours actually something special happens he finds out
something special happens he finds out
something special happens he finds out that there’s even better way to score
that there’s even better way to score
that there’s even better way to score points basically by tunneling which was
points basically by tunneling which was
points basically by tunneling which was see in a second so it’s pretty good so
see in a second so it’s pretty good so
see in a second so it’s pretty good so yeah basically someone yeah he update
yeah basically someone yeah he update
yeah basically someone yeah he update this model by basically by the rewards
this model by basically by the rewards
this model by basically by the rewards he gets so try game of the game of the
he gets so try game of the game of the
he gets so try game of the game of the game of the game and he makes a decision
game of the game and he makes a decision
game of the game and he makes a decision tree basically and each decision he
tree basically and each decision he
tree basically and each decision he makes has a certain probability for
makes has a certain probability for
makes has a certain probability for certain reward and it tries keeps
certain reward and it tries keeps
certain reward and it tries keeps updating it based on experience and
updating it based on experience and
updating it based on experience and eventually it does pretty well and
eventually it does pretty well and
eventually it does pretty well and deepmind is for all kinds of Atari games
deepmind is for all kinds of Atari games
deepmind is for all kinds of Atari games and actually showed it as basically a
and actually showed it as basically a
and actually showed it as basically a possibility for generic intelligence
possibility for generic intelligence
possibility for generic intelligence there for the fact that there was no
there for the fact that there was no
there for the fact that there was no domain knowledge previously involved it
domain knowledge previously involved it
domain knowledge previously involved it was capable of solving several a fairy
was capable of solving several a fairy
was capable of solving several a fairy stars for all kinds of Atari games but
stars for all kinds of Atari games but
stars for all kinds of Atari games but there’s also yeah you could say it’s
there’s also yeah you could say it’s
there’s also yeah you could say it’s subset of reinforcement learning
subset of reinforcement learning
subset of reinforcement learning it’s called genetic algorithms most if
it’s called genetic algorithms most if
it’s called genetic algorithms most if you’ve heard about it basically it
you’ve heard about it basically it
you’ve heard about it basically it doesn’t it’s it’s a little bit different
doesn’t it’s it’s a little bit different
doesn’t it’s it’s a little bit different here you take one model and keep
here you take one model and keep
here you take one model and keep training that genetic algorithm works a
training that genetic algorithm works a
training that genetic algorithm works a little bit different there’s a nice
little bit different there’s a nice
little bit different there’s a nice example on the internet not this one yep
example on the internet not this one yep
example on the internet not this one yep I wonder how he trained by the way
anyway this is an example for genetic
anyway this is an example for genetic algorithm Walker basically well it does
algorithm Walker basically well it does
algorithm Walker basically well it does every generation he froze had 10 models
every generation he froze had 10 models
every generation he froze had 10 models there’s based on how far someone can get
there’s based on how far someone can get
there’s based on how far someone can get so how much reward he gets in one model
so how much reward he gets in one model
so how much reward he gets in one model one run it determines who lives and dies
one run it determines who lives and dies
one run it determines who lives and dies and who may reproduce so for example
and who may reproduce so for example
and who may reproduce so for example I’ve configured this one from champions
I’ve configured this one from champions
I’ve configured this one from champions to copy to if you see it there so only
to copy to if you see it there so only
to copy to if you see it there so only if
if
if you win the game in your first two
you win the game in your first two
you win the game in your first two positions you just go on to the next
positions you just go on to the next
positions you just go on to the next round and the rest of them either get
round and the rest of them either get
round and the rest of them either get killed off or are being crossed over
killed off or are being crossed over
killed off or are being crossed over so basically properties from one mole
so basically properties from one mole
so basically properties from one mole will be combined with crops to other
will be combined with crops to other
will be combined with crops to other models and thus optimizing or make it in
models and thus optimizing or make it in
models and thus optimizing or make it in good worse depends and each time you
good worse depends and each time you
good worse depends and each time you keep going on and on and on and then
keep going on and on and on and then
keep going on and on and on and then keep track of the optimal scores so also
keep track of the optimal scores so also
keep track of the optimal scores so also there are a lot of algorithms to choose
there are a lot of algorithms to choose
there are a lot of algorithms to choose from so it’s really important to have a
from so it’s really important to have a
from so it’s really important to have a grasp on what you want to solve how you
grasp on what you want to solve how you
grasp on what you want to solve how you want to solve it and what you need to
want to solve it and what you need to
want to solve it and what you need to solve it so how is it applied in
solve it so how is it applied in
solve it so how is it applied in everyday life in short you can see
everyday life in short you can see
everyday life in short you can see several applications already running
several applications already running
several applications already running with it where the forecast for Amsterdam
with it where the forecast for Amsterdam
with it where the forecast for Amsterdam there’s a filtration system that
there’s a filtration system that
there’s a filtration system that actually can predict whether or not
actually can predict whether or not
actually can predict whether or not something is going to fill or something
something is going to fill or something
something is going to fill or something needs attention automatic translation so
needs attention automatic translation so
needs attention automatic translation so this is actually several problems in
this is actually several problems in
this is actually several problems in one’s one so you have image recognition
one’s one so you have image recognition
one’s one so you have image recognition Dave in translation they have to be well
Dave in translation they have to be well
Dave in translation they have to be well we display that translation on the image
we display that translation on the image
we display that translation on the image again so and this is actually cancer
again so and this is actually cancer
again so and this is actually cancer detection so on a very low level
detection so on a very low level
detection so on a very low level determining what’s probability that
determining what’s probability that
determining what’s probability that something may be out of place spam
something may be out of place spam
something may be out of place spam filters of course and a test lock car so
filters of course and a test lock car so
filters of course and a test lock car so how would you get started so I’m gonna
how would you get started so I’m gonna
how would you get started so I’m gonna be very short but there’s basically two
be very short but there’s basically two
be very short but there’s basically two ways to get start it is just used to pre
ways to get start it is just used to pre
ways to get start it is just used to pre train models like the fishing API I just
train models like the fishing API I just
train models like the fishing API I just show just use it in your application and
show just use it in your application and
show just use it in your application and well don’t reinvent the wheel for simple
well don’t reinvent the wheel for simple
well don’t reinvent the wheel for simple facts yeah there are people out there
facts yeah there are people out there
facts yeah there are people out there that did it before you and you probably
that did it before you and you probably
that did it before you and you probably are not going to do it much better so as
are not going to do it much better so as
are not going to do it much better so as I mentioned before there’s a Google
I mentioned before there’s a Google
I mentioned before there’s a Google Cloud ml IBM bluemix microfiche or etc
Cloud ml IBM bluemix microfiche or etc
Cloud ml IBM bluemix microfiche or etc etc or you can build your own and tweak
etc or you can build your own and tweak
etc or you can build your own and tweak with your own but
with your own but
with your own but then I would suggest first of all learn
then I would suggest first of all learn
then I would suggest first of all learn Python yes you can use most libraries
Python yes you can use most libraries
Python yes you can use most libraries with Java Scala I love those but
with Java Scala I love those but
with Java Scala I love those but basically the data science and machine
basically the data science and machine
basically the data science and machine learning areas everything is Python so
learning areas everything is Python so
learning areas everything is Python so every example you’ll see is bite and
every example you’ll see is bite and
every example you’ll see is bite and every notebook you’ll see spied so at
every notebook you’ll see spied so at
every notebook you’ll see spied so at the beginning just learn Python and if
the beginning just learn Python and if
the beginning just learn Python and if you’re comfortable enough with
you’re comfortable enough with
you’re comfortable enough with everything maybe then move on to another
everything maybe then move on to another
everything maybe then move on to another one other language in subtitle notebook
one other language in subtitle notebook
one other language in subtitle notebook really install it and try to online guys
really install it and try to online guys
really install it and try to online guys there plenty of them they’re very good
there plenty of them they’re very good
there plenty of them they’re very good and you will be fool if you don’t use it
and you will be fool if you don’t use it
and you will be fool if you don’t use it well for example machine learning
well for example machine learning
well for example machine learning libraries that you could use if you want
libraries that you could use if you want
libraries that you could use if you want to do it on your own are tensorflow
to do it on your own are tensorflow
to do it on your own are tensorflow actually TF learn or Kara’s torch which
actually TF learn or Kara’s torch which
actually TF learn or Kara’s torch which is newer
is newer
is newer Tianna peyten deep learning for J’s
Tianna peyten deep learning for J’s
Tianna peyten deep learning for J’s someone did do it
someone did do it
someone did do it Java and cough it to for enter several
Java and cough it to for enter several
Java and cough it to for enter several others but these are the memos for those
others but these are the memos for those
others but these are the memos for those who are wondering really what is ten
who are wondering really what is ten
who are wondering really what is ten flow in the basics isn’t graph based
flow in the basics isn’t graph based
flow in the basics isn’t graph based calculation framework so the libraries
calculation framework so the libraries
calculation framework so the libraries on top of its support machine learning
on top of its support machine learning
on top of its support machine learning but in essence is a graph based
but in essence is a graph based
but in essence is a graph based calculation framework which optimizes
calculation framework which optimizes
calculation framework which optimizes for parallelization and other things
for parallelization and other things
for parallelization and other things like running on the CPU keep you GPU
like running on the CPU keep you GPU
like running on the CPU keep you GPU parallelization or several processes etc
well also not if anyone saw the talk
well also not if anyone saw the talk yesterday about the data analysis yeah
yesterday about the data analysis yeah
yesterday about the data analysis yeah it is a very important aspect first of
it is a very important aspect first of
it is a very important aspect first of all you want to frame the problem I
all you want to frame the problem I
all you want to frame the problem I didn’t find what you want to solve for
didn’t find what you want to solve for
didn’t find what you want to solve for example with the housing data yeah what
example with the housing data yeah what
example with the housing data yeah what do you want to solve do you really want
do you want to solve do you really want
do you want to solve do you really want to know the prices or just you not want
to know the prices or just you not want
to know the prices or just you not want to know how expensive is it expensive or
to know how expensive is it expensive or
to know how expensive is it expensive or cheap so you have to adjust the data as
cheap so you have to adjust the data as
cheap so you have to adjust the data as well
well
well cleaning up filter it and adjust it
cleaning up filter it and adjust it
cleaning up filter it and adjust it where I need you need to look at a
where I need you need to look at a
where I need you need to look at a bigger picture basically what’s gonna
bigger picture basically what’s gonna
bigger picture basically what’s gonna come before and what’s coming after your
come before and what’s coming after your
come before and what’s coming after your machine
machine
machine so the reason why I predict housing
so the reason why I predict housing
so the reason why I predict housing prices is not because you’re such a fan
prices is not because you’re such a fan
prices is not because you’re such a fan of houses we usually usually usually
of houses we usually usually usually
of houses we usually usually usually it’s because there’s another process
it’s because there’s another process
it’s because there’s another process after you which really needs that
after you which really needs that
after you which really needs that information well third point check your
information well third point check your
information well third point check your assumptions because you have those and
assumptions because you have those and
assumptions because you have those and they’re usually wrong and visualized
they’re usually wrong and visualized
they’re usually wrong and visualized again in the pie to notebook if you have
again in the pie to notebook if you have
again in the pie to notebook if you have an ID form model if you have an idea of
an ID form model if you have an idea of
an ID form model if you have an idea of how the data says you do if you think
how the data says you do if you think
how the data says you do if you think your machine learning should work
your machine learning should work
your machine learning should work visualize it
visualize it
visualize it visualize every steps see how it outputs
visualize every steps see how it outputs
visualize every steps see how it outputs not don’t put it in your application at
not don’t put it in your application at
not don’t put it in your application at once the future of AI well as I saw it
once the future of AI well as I saw it
once the future of AI well as I saw it went quite rapidly last few years so
went quite rapidly last few years so
went quite rapidly last few years so rapid that’s unimaginable actually for
rapid that’s unimaginable actually for
rapid that’s unimaginable actually for example this is the police agent from –
example this is the police agent from –
example this is the police agent from – by 2030 Dubai is intending to have I
by 2030 Dubai is intending to have I
by 2030 Dubai is intending to have I believe 50% of police force replaced by
believe 50% of police force replaced by
believe 50% of police force replaced by these things
these things
these things however it’s no more than a walk-in
however it’s no more than a walk-in
however it’s no more than a walk-in kiosk at the moment on the other hand we
kiosk at the moment on the other hand we
kiosk at the moment on the other hand we have Boston Dynamics which is actually
have Boston Dynamics which is actually
have Boston Dynamics which is actually military ex-military contract from
military ex-military contract from
military ex-military contract from Google and these are no jokes and
Google and these are no jokes and
Google and these are no jokes and another thing about what Google recently
another thing about what Google recently
another thing about what Google recently released it for example two papers
released it for example two papers
released it for example two papers regarding
regarding
regarding relational networks so these are special
relational networks so these are special
relational networks so these are special networks that want we have plug ball in
networks that want we have plug ball in
networks that want we have plug ball in order
order
order neural networks which we want to use to
neural networks which we want to use to
neural networks which we want to use to answer question like this there’s a tiny
answer question like this there’s a tiny
answer question like this there’s a tiny rubber fing there’s the same color it’s
rubber fing there’s the same color it’s
rubber fing there’s the same color it’s a large cylinder what shape is it so
a large cylinder what shape is it so
a large cylinder what shape is it so tiny rubber feet the same color is this
tiny rubber feet the same color is this
tiny rubber feet the same color is this big thing so for us it’s already a few
big thing so for us it’s already a few
big thing so for us it’s already a few steps and actually they prove that they
steps and actually they prove that they
steps and actually they prove that they were capable of answering this question
were capable of answering this question
were capable of answering this question with quite better than human proficiency
with quite better than human proficiency
with quite better than human proficiency so yeah we can’t expect a lot more in
so yeah we can’t expect a lot more in
so yeah we can’t expect a lot more in the near future
the near future
the near future regarding this so here’s some resources
regarding this so here’s some resources
regarding this so here’s some resources also that you really should check out I
also that you really should check out I
also that you really should check out I really would suggest look look another
really would suggest look look another
really would suggest look look another one good hands-on is actually this one
one good hands-on is actually this one
one good hands-on is actually this one or real alien zero
or real alien zero
or real alien zero I probably pronounced it wrong but II
I probably pronounced it wrong but II
I probably pronounced it wrong but II wrote a whole book put this whole all
wrote a whole book put this whole all
wrote a whole book put this whole all these notebooks online on get up and
these notebooks online on get up and
these notebooks online on get up and give you really a good introduction into
give you really a good introduction into
give you really a good introduction into data science side kid tends to flow all
data science side kid tends to flow all
data science side kid tends to flow all those things it will take time but sorry
it’s also the O’Reilly book he published
it’s also the O’Reilly book he published a Riley book yeah the sidekick I don’t
a Riley book yeah the sidekick I don’t
a Riley book yeah the sidekick I don’t know remember the tank yes I don’t know
know remember the tank yes I don’t know
know remember the tank yes I don’t know what he said introduction but basically
what he said introduction but basically
what he said introduction but basically yes I can tell flow is this big thick
yes I can tell flow is this big thick
yes I can tell flow is this big thick it’s a good read no yes and the slides
it’s a good read no yes and the slides
it’s a good read no yes and the slides really represent this book as well so
really represent this book as well so
really represent this book as well so it’s really really important to look at
it’s really really important to look at
it’s really really important to look at this if you want so these are some other
this if you want so these are some other
this if you want so these are some other miscellaneous sources imagenet this is
miscellaneous sources imagenet this is
miscellaneous sources imagenet this is for example research for all kinds of
for example research for all kinds of
for example research for all kinds of images and computation basically to
images and computation basically to
images and computation basically to check how good your facial recognition
check how good your facial recognition
check how good your facial recognition is immature canadian-ish open AI is a
is immature canadian-ish open AI is a
is immature canadian-ish open AI is a well platform promotion open AI and they
well platform promotion open AI and they
well platform promotion open AI and they also have an open-air gym for competing
also have an open-air gym for competing
also have an open-air gym for competing for several problems and what I just
for several problems and what I just
for several problems and what I just showed you is a genetic algorithm well
showed you is a genetic algorithm well
showed you is a genetic algorithm well walkers which is basically simple
walkers which is basically simple
walkers which is basically simple genetic fun any questions
Be First to Comment