Press "Enter" to skip to content

Learning from the brain for the technologies of the future | Bart ter Haar Romeny | TEDxEindhoven


like golf moments that’s what it’s all

like golf moments that’s what it’s all about and a light bill of course at this

about and a light bill of course at this

about and a light bill of course at this city of Philips as a medical meeting and

city of Philips as a medical meeting and

city of Philips as a medical meeting and a light belt means a bright idea and

a light belt means a bright idea and

a light belt means a bright idea and ideas where do they come from they come

ideas where do they come from they come

ideas where do they come from they come from the brain that the brain is today

from the brain that the brain is today

from the brain that the brain is today actually being discovered in a way that

actually being discovered in a way that

actually being discovered in a way that you won’t believe we can look inside the

you won’t believe we can look inside the

you won’t believe we can look inside the brain at incredible resolution we can

brain at incredible resolution we can

brain at incredible resolution we can see what the brain is doing we have deep

see what the brain is doing we have deep

see what the brain is doing we have deep learning etc and that’s what I will talk

learning etc and that’s what I will talk

learning etc and that’s what I will talk a little bit about today what is in this

a little bit about today what is in this

a little bit about today what is in this brain happening I’m working at the

brain happening I’m working at the

brain happening I’m working at the University and my field is pattern

University and my field is pattern

University and my field is pattern recognition

recognition

recognition I designed with my whole team automatic

I designed with my whole team automatic

I designed with my whole team automatic software to find tumors patterns in lots

software to find tumors patterns in lots

software to find tumors patterns in lots of medical images at the best pattern

of medical images at the best pattern

of medical images at the best pattern recognition machine is this guy

recognition machine is this guy

recognition machine is this guy that’s an amazing pattern recognition

that’s an amazing pattern recognition

that’s an amazing pattern recognition how do you design all this and I said

how do you design all this and I said

how do you design all this and I said okay let’s be inspired by this brain

okay let’s be inspired by this brain

okay let’s be inspired by this brain let’s see what’s in there

let’s see what’s in there

let’s see what’s in there so insight is this magic thing Eureka

so insight is this magic thing Eureka

so insight is this magic thing Eureka and I want to take you on a journey what

and I want to take you on a journey what

and I want to take you on a journey what do we know how can we learn from this

do we know how can we learn from this

do we know how can we learn from this how can it be how can it inspire us so

how can it be how can it inspire us so

how can it be how can it inspire us so let’s start with some facts of our brain

let’s start with some facts of our brain

let’s start with some facts of our brain it’s incredibly small it’s only about a

it’s incredibly small it’s only about a

it’s incredibly small it’s only about a kilo 2% the far away that used a lot of

kilo 2% the far away that used a lot of

kilo 2% the far away that used a lot of energy 20% of our energy and it has an

energy 20% of our energy and it has an

energy 20% of our energy and it has an incredible amount of neurons 86 billion

incredible amount of neurons 86 billion

incredible amount of neurons 86 billion at the nerve fibers they’re all

at the nerve fibers they’re all

at the nerve fibers they’re all connected to each other all these nerves

connected to each other all these nerves

connected to each other all these nerves spiders wire a thin micron thin all the

spiders wire a thin micron thin all the

spiders wire a thin micron thin all the wires together is bordered to the moon

wires together is bordered to the moon

wires together is bordered to the moon and back the connections between these

and back the connections between these

and back the connections between these neurons are called synapses we have

neurons are called synapses we have

neurons are called synapses we have amazing amount of shine obsessed and

amazing amount of shine obsessed and

amazing amount of shine obsessed and it’s an computer outperforming all our

it’s an computer outperforming all our

it’s an computer outperforming all our other computers they have calculated

other computers they have calculated

other computers they have calculated it’s about one petaflop

it’s about one petaflop

it’s about one petaflop floating-point operations per seconds

floating-point operations per seconds

floating-point operations per seconds so let’s put a little bit more in

so let’s put a little bit more in

so let’s put a little bit more in perspective if you see the trees in the

perspective if you see the trees in the

perspective if you see the trees in the Amazon forest and the neurons in your

Amazon forest and the neurons in your

Amazon forest and the neurons in your brain

brain

brain it’s about the same number if you look

it’s about the same number if you look

it’s about the same number if you look at the neuron it has connections one

at the neuron it has connections one

at the neuron it has connections one neuron is connected to 50,000 other

neuron is connected to 50,000 other

neuron is connected to 50,000 other neurons so that’s quite an broad spread

neurons so that’s quite an broad spread

neurons so that’s quite an broad spread out and if you look at these sign lapses

out and if you look at these sign lapses

out and if you look at these sign lapses and we have trillions of these synapses

and we have trillions of these synapses

and we have trillions of these synapses how do we learn if you use a synapse

how do we learn if you use a synapse

how do we learn if you use a synapse many times it gets bigger and if you

many times it gets bigger and if you

many times it gets bigger and if you forget it gets smaller so by repetitive

forget it gets smaller so by repetitive

forget it gets smaller so by repetitive action you learn so we can also now see

action you learn so we can also now see

action you learn so we can also now see how this learning can be done and one of

how this learning can be done and one of

how this learning can be done and one of the amazing feat of our brain is that

the amazing feat of our brain is that

the amazing feat of our brain is that this guy is only using 25 watt and

this guy is only using 25 watt and

this guy is only using 25 watt and that’s quite stunning and if we look at

that’s quite stunning and if we look at

that’s quite stunning and if we look at our computers today we look at these

our computers today we look at these

our computers today we look at these Google data centers and so on and all

Google data centers and so on and all

Google data centers and so on and all these computing and Amazon computing

these computing and Amazon computing

these computing and Amazon computing centers they use megawatts they have

centers they use megawatts they have

centers they use megawatts they have cooling towers on top and that’s a waste

cooling towers on top and that’s a waste

cooling towers on top and that’s a waste of energy they’re just incredible so we

of energy they’re just incredible so we

of energy they’re just incredible so we should learn so much more from this this

should learn so much more from this this

should learn so much more from this this brain so how is it wired

brain so how is it wired

brain so how is it wired how’s it work what do these functional

how’s it work what do these functional

how’s it work what do these functional circuits actually do and we have a

circuits actually do and we have a

circuits actually do and we have a community now in the world that’s really

community now in the world that’s really

community now in the world that’s really focusing on can we mimic this brain use

focusing on can we mimic this brain use

focusing on can we mimic this brain use this incredible computing algorithms and

this incredible computing algorithms and

this incredible computing algorithms and then apply them in our clever technology

then apply them in our clever technology

then apply them in our clever technology I go a little bit deeper in that let’s

I go a little bit deeper in that let’s

I go a little bit deeper in that let’s first tell it the brain how can we

first tell it the brain how can we

first tell it the brain how can we measure this well the first of all is

measure this well the first of all is

measure this well the first of all is and that’s me and one of the biggest

and that’s me and one of the biggest

and that’s me and one of the biggest companies in the world making all these

companies in the world making all these

companies in the world making all these fantastic machines is right here

fantastic machines is right here

fantastic machines is right here it’s Philips it’s in the top three they

it’s Philips it’s in the top three they

it’s Philips it’s in the top three they make MRI machine CT machines etc we can

make MRI machine CT machines etc we can

make MRI machine CT machines etc we can now see the brain and incredible

now see the brain and incredible

now see the brain and incredible resolution of resolutions now about a

resolution of resolutions now about a

resolution of resolutions now about a quarter of a millimeter so this is

quarter of a millimeter so this is

quarter of a millimeter so this is called an MRI scan and this is my own

called an MRI scan and this is my own

called an MRI scan and this is my own brain slice by slice you can see every

brain slice by slice you can see every

brain slice by slice you can see every quarter of a millimeter in this brain

quarter of a millimeter in this brain

quarter of a millimeter in this brain you see in the middle the rested spinal

you see in the middle the rested spinal

you see in the middle the rested spinal cords connecting all these fibers to my

cords connecting all these fibers to my

cords connecting all these fibers to my muscles to my heart so everything but

muscles to my heart so everything but

muscles to my heart so everything but this is not only we can see we could

this is not only we can see we could

this is not only we can see we could also see function and how can we see

also see function and how can we see

also see function and how can we see function if a brain cell is active

function if a brain cell is active

function if a brain cell is active suppose I do like this then my motor

suppose I do like this then my motor

suppose I do like this then my motor court

court

court is active and these cells they generate

is active and these cells they generate

is active and these cells they generate action potentials they need oxygen they

action potentials they need oxygen they

action potentials they need oxygen they need food so they give a signal to the

need food so they give a signal to the

need food so they give a signal to the small capillaries to the small blood

small capillaries to the small blood

small capillaries to the small blood vessels open and bring me oxygen an

vessels open and bring me oxygen an

vessels open and bring me oxygen an oxygen can be seen on an MRI scan so you

oxygen can be seen on an MRI scan so you

oxygen can be seen on an MRI scan so you first do nothing you make a scan and

first do nothing you make a scan and

first do nothing you make a scan and then you do this and if you take the

then you do this and if you take the

then you do this and if you take the difference of these kinds you see a tiny

difference of these kinds you see a tiny

difference of these kinds you see a tiny difference and now you see this boy is

difference and now you see this boy is

difference and now you see this boy is looking at the screen he’s using his

looking at the screen he’s using his

looking at the screen he’s using his visual system and the back of our brain

visual system and the back of our brain

visual system and the back of our brain is for vision and you see that’s quite a

is for vision and you see that’s quite a

is for vision and you see that’s quite a lot this for vision a quarter of our

lot this for vision a quarter of our

lot this for vision a quarter of our brain is for vision and if you see how

brain is for vision and if you see how

brain is for vision and if you see how many nerve cells we have so how many

many nerve cells we have so how many

many nerve cells we have so how many filters how many calculations are done

filters how many calculations are done

filters how many calculations are done vision is an incredible thing we are

vision is an incredible thing we are

vision is an incredible thing we are purely visual machines because images

purely visual machines because images

purely visual machines because images came on the internet it exploded we do

came on the internet it exploded we do

came on the internet it exploded we do nothing else than look at images because

nothing else than look at images because

nothing else than look at images because our brain is made for images we are

our brain is made for images we are

our brain is made for images we are images machines so we have functions we

images machines so we have functions we

images machines so we have functions we can do more we also look at connections

can do more we also look at connections

can do more we also look at connections how can you measure connections in the

how can you measure connections in the

how can you measure connections in the brain well they found some years ago

brain well they found some years ago

brain well they found some years ago that you can measure in an MRI scan the

that you can measure in an MRI scan the

that you can measure in an MRI scan the very tiny motion of water molecules they

very tiny motion of water molecules they

very tiny motion of water molecules they make the magnetic field to the left a

make the magnetic field to the left a

make the magnetic field to the left a little bit different than to the right

little bit different than to the right

little bit different than to the right and if you move a little bit they change

and if you move a little bit they change

and if you move a little bit they change the magnetic field will change in

the magnetic field will change in

the magnetic field will change in frequency and if water is just

frequency and if water is just

frequency and if water is just surrounded by water it goes in every

surrounded by water it goes in every

surrounded by water it goes in every direction you see a little bit like a

direction you see a little bit like a

direction you see a little bit like a sphere but if water is in a nerve fiber

sphere but if water is in a nerve fiber

sphere but if water is in a nerve fiber it can only move along the nerve fiber

it can only move along the nerve fiber

it can only move along the nerve fiber and not so much the other way so if you

and not so much the other way so if you

and not so much the other way so if you look for some time you see you kind of

look for some time you see you kind of

look for some time you see you kind of an ellipsoid well the long axis of the

an ellipsoid well the long axis of the

an ellipsoid well the long axis of the ellipsoid is of course the direction of

ellipsoid is of course the direction of

ellipsoid is of course the direction of the fiber and what you can do in every

the fiber and what you can do in every

the fiber and what you can do in every voxel you measure these millions of

voxel you measure these millions of

voxel you measure these millions of foxholes you connect them and then you

foxholes you connect them and then you

foxholes you connect them and then you get the wires in my group we studied

get the wires in my group we studied

get the wires in my group we studied this for a long time because we really

this for a long time because we really

this for a long time because we really wanted to see how is this whole brain

wanted to see how is this whole brain

wanted to see how is this whole brain Wyatt

Wyatt

Wyatt losses passed before neurosurgeons they

losses passed before neurosurgeons they

losses passed before neurosurgeons they need to see what are the major tracks if

need to see what are the major tracks if

need to see what are the major tracks if you remove a tumor you don’t want to

you remove a tumor you don’t want to

you remove a tumor you don’t want to make the patient blind or paralyzed you

make the patient blind or paralyzed you

make the patient blind or paralyzed you need to prepare all this so what we did

need to prepare all this so what we did

need to prepare all this so what we did is we made fantastic

is we made fantastic

is we made fantastic visualizations we program this in the

visualizations we program this in the

visualizations we program this in the GPU you see the fibers here connect

GPU you see the fibers here connect

GPU you see the fibers here connect the left and the rights in the brain the

the left and the rights in the brain the

the left and the rights in the brain the colors are X Y Z is red green blue so we

colors are X Y Z is red green blue so we

colors are X Y Z is red green blue so we have some color coding as well this

have some color coding as well this

have some color coding as well this cannot be done for all the areas in the

cannot be done for all the areas in the

cannot be done for all the areas in the brain how we here how we see how we move

brain how we here how we see how we move

brain how we here how we see how we move so we have now the the wires of power

so we have now the the wires of power

so we have now the the wires of power electronic electronic schematic and the

electronic electronic schematic and the

electronic electronic schematic and the visual system is the most study Teufel

visual system is the most study Teufel

visual system is the most study Teufel and I’m going to go a little bit deeper

and I’m going to go a little bit deeper

and I’m going to go a little bit deeper in the visual system they made all these

in the visual system they made all these

in the visual system they made all these measurements and they looked how does it

measurements and they looked how does it

measurements and they looked how does it work and it turns out they’re in stages

work and it turns out they’re in stages

work and it turns out they’re in stages about 11 stages these stages have been

about 11 stages these stages have been

about 11 stages these stages have been named the primary visual cortex a stage

named the primary visual cortex a stage

named the primary visual cortex a stage number one that’s in the back of our

number one that’s in the back of our

number one that’s in the back of our head it’s called v1 then v2 v3 v4

head it’s called v1 then v2 v3 v4

head it’s called v1 then v2 v3 v4 they’re connected you see the

they’re connected you see the

they’re connected you see the connections and these layers we can move

connections and these layers we can move

connections and these layers we can move these layers by looking at that’s model

these layers by looking at that’s model

these layers by looking at that’s model one neuron and then model thousands of

one neuron and then model thousands of

one neuron and then model thousands of neurons and millions of neurons and the

neurons and millions of neurons and the

neurons and millions of neurons and the model egg goes by modeling these

model egg goes by modeling these

model egg goes by modeling these synapses and these synapses are

synapses and these synapses are

synapses and these synapses are connected by what we call weights in a

connected by what we call weights in a

connected by what we call weights in a neural network everybody has heard about

neural network everybody has heard about

neural network everybody has heard about neural networks artificial intelligence

neural networks artificial intelligence

neural networks artificial intelligence is exactly what we do what we actually

is exactly what we do what we actually

is exactly what we do what we actually do is we mimic all these connections

do is we mimic all these connections

do is we mimic all these connections what happens in the brain and people

what happens in the brain and people

what happens in the brain and people made these neural networks you see a

made these neural networks you see a

made these neural networks you see a three layer neural network and what you

three layer neural network and what you

three layer neural network and what you put in this network has to be a

put in this network has to be a

put in this network has to be a classifier you put in lots of images and

classifier you put in lots of images and

classifier you put in lots of images and the network has to say what is it it’s

the network has to say what is it it’s

the network has to say what is it it’s the cat this the dog is it the horse but

the cat this the dog is it the horse but

the cat this the dog is it the horse but these little networks were actually for

these little networks were actually for

these little networks were actually for years not working so well it was

years not working so well it was

years not working so well it was terrible it was 75 maybe 80 percent and

terrible it was 75 maybe 80 percent and

terrible it was 75 maybe 80 percent and that’s not good enough

that’s not good enough

that’s not good enough so we struggles and we have major

so we struggles and we have major

so we struggles and we have major competitions in 2010 we had these big

competitions in 2010 we had these big

competitions in 2010 we had these big yeah gruel images coming up we had

yeah gruel images coming up we had

yeah gruel images coming up we had access to millions of images and people

access to millions of images and people

access to millions of images and people started to make competitions they said

started to make competitions they said

started to make competitions they said ok sending your program we have here 1.2

ok sending your program we have here 1.2

ok sending your program we have here 1.2 million images 1,000 classes is that the

million images 1,000 classes is that the

million images 1,000 classes is that the horses at the beach is this building and

horses at the beach is this building and

horses at the beach is this building and people were in about 2010 75% correct

people were in about 2010 75% correct

people were in about 2010 75% correct today we are 96% because what happens it

today we are 96% because what happens it

today we are 96% because what happens it was about 2012 people had a major

was about 2012 people had a major

was about 2012 people had a major invention and actually that invention

invention and actually that invention

invention and actually that invention was you should not take three layers in

was you should not take three layers in

was you should not take three layers in a neural network but you shake should

a neural network but you shake should

a neural network but you shake should take many many more layers more not only

take many many more layers more not only

take many many more layers more not only 10 maybe go to 20 you maybe go to 100

10 maybe go to 20 you maybe go to 100

10 maybe go to 20 you maybe go to 100 and that’s called deep so that’s what we

and that’s called deep so that’s what we

and that’s called deep so that’s what we call deep learning we can train these

call deep learning we can train these

call deep learning we can train these networks and this network was yeah what

networks and this network was yeah what

networks and this network was yeah what is the network like this doing stage one

is the network like this doing stage one

is the network like this doing stage one is doing very simple things if there’s

is doing very simple things if there’s

is doing very simple things if there’s only filters to find some lines some

only filters to find some lines some

only filters to find some lines some edges very primitive things the second

edges very primitive things the second

edges very primitive things the second stage is doing some more complex things

stage is doing some more complex things

stage is doing some more complex things so these lines are now triangles so it

so these lines are now triangles so it

so these lines are now triangles so it finds noses eyes and so on so parts the

finds noses eyes and so on so parts the

finds noses eyes and so on so parts the third one finds objects finds a face and

third one finds objects finds a face and

third one finds objects finds a face and so on so you get more contextual areas

so on so you get more contextual areas

so on so you get more contextual areas if you go deeper in the brain

what made it especially happen well we

what made it especially happen well we have now really amount of enormous

have now really amount of enormous

have now really amount of enormous amounts of data we don’t talk about

amounts of data we don’t talk about

amounts of data we don’t talk about millions of images we talk about

millions of images we talk about

millions of images we talk about trillions of images so that’s what we

trillions of images so that’s what we

trillions of images so that’s what we call big data we also have GPUs graphics

call big data we also have GPUs graphics

call big data we also have GPUs graphics processing units that’s actually game

processing units that’s actually game

processing units that’s actually game cards people wanted to play games and if

cards people wanted to play games and if

cards people wanted to play games and if you play games you have to generate all

you play games you have to generate all

you play games you have to generate all kinds of 3d artificial environments and

kinds of 3d artificial environments and

kinds of 3d artificial environments and the computers were not fast enough so

the computers were not fast enough so

the computers were not fast enough so they said ok let’s make many small

they said ok let’s make many small

they said ok let’s make many small parallel computers one computer per

parallel computers one computer per

parallel computers one computer per pixel and then we can generate thousand

pixel and then we can generate thousand

pixel and then we can generate thousand pixels at a time and that’s exactly what

pixels at a time and that’s exactly what

pixels at a time and that’s exactly what everybody wanted to have so it costs

everybody wanted to have so it costs

everybody wanted to have so it costs nothing the GPU is in every computer now

nothing the GPU is in every computer now

nothing the GPU is in every computer now and it’s actually a small computer with

and it’s actually a small computer with

and it’s actually a small computer with 1000 processors in there and it costs 52

1000 processors in there and it costs 52

1000 processors in there and it costs 52 to a few hundred euros it’s made here by

to a few hundred euros it’s made here by

to a few hundred euros it’s made here by a SML they make the machines who make it

a SML they make the machines who make it

a SML they make the machines who make it so that’s now available and the third

so that’s now available and the third

so that’s now available and the third step is of course we realized that we

step is of course we realized that we

step is of course we realized that we can have deep neural networks and

can have deep neural networks and

can have deep neural networks and there’s a huge community now it’s

there’s a huge community now it’s

there’s a huge community now it’s exploding and the trick is of course to

exploding and the trick is of course to

exploding and the trick is of course to the upper

the upper

the upper you see the visual system in the middle

you see the visual system in the middle

you see the visual system in the middle of you see these all these layers these

of you see these all these layers these

of you see these all these layers these layers and we see an increasing context

layers and we see an increasing context

layers and we see an increasing context but let’s go a little bit deeper into

but let’s go a little bit deeper into

but let’s go a little bit deeper into the brain what did they find in vision

the brain what did they find in vision

the brain what did they find in vision if you cut the brain you see that this

if you cut the brain you see that this

if you cut the brain you see that this actually it has layers it has lots it’s

actually it has layers it has lots it’s

actually it has layers it has lots it’s incredibly well organized not a single

incredibly well organized not a single

incredibly well organized not a single neuron is on the wrong place that every

neuron is on the wrong place that every

neuron is on the wrong place that every neuron is used if you don’t use in their

neuron is used if you don’t use in their

neuron is used if you don’t use in their own it generates so people did lots of

own it generates so people did lots of

own it generates so people did lots of experiments they stuck a needle in v1 v2

experiments they stuck a needle in v1 v2

experiments they stuck a needle in v1 v2 v3 and what is the cell seeing and there

v3 and what is the cell seeing and there

v3 and what is the cell seeing and there so indeed if you stick a needle in these

so indeed if you stick a needle in these

so indeed if you stick a needle in these very primitive first layers v1 you saw

very primitive first layers v1 you saw

very primitive first layers v1 you saw these very simple filters coming up it’s

these very simple filters coming up it’s

these very simple filters coming up it’s exactly what’s happening there so in the

exactly what’s happening there so in the

exactly what’s happening there so in the first layer we do these primitive things

first layer we do these primitive things

first layer we do these primitive things and in mathematics we say ok we take

and in mathematics we say ok we take

and in mathematics we say ok we take derivatives the first derivative is

derivatives the first derivative is

derivatives the first derivative is actually the change in intensity

actually the change in intensity

actually the change in intensity these are edges second derivative how

these are edges second derivative how

these are edges second derivative how corrupt is it so we can do mathematics

corrupt is it so we can do mathematics

corrupt is it so we can do mathematics and the brain is actually doing a lot of

and the brain is actually doing a lot of

and the brain is actually doing a lot of mathematics here we can also look at how

mathematics here we can also look at how

mathematics here we can also look at how is this formed in the brain how do these

is this formed in the brain how do these

is this formed in the brain how do these receptive fields as we call them these

receptive fields as we call them these

receptive fields as we call them these filters how did they originate and it

filters how did they originate and it

filters how did they originate and it turns out you are not born with these

turns out you are not born with these

turns out you are not born with these filters if you’re born every neuron is

filters if you’re born every neuron is

filters if you’re born every neuron is connected to every other neuron in its

connected to every other neuron in its

connected to every other neuron in its neighborhood so how can it get organized

neighborhood so how can it get organized

neighborhood so how can it get organized it organizes itself the first three

it organizes itself the first three

it organizes itself the first three months after birth you make them so

months after birth you make them so

months after birth you make them so that’s quite exciting so we said let’s

that’s quite exciting so we said let’s

that’s quite exciting so we said let’s look at an image and take a monkey and a

look at an image and take a monkey and a

look at an image and take a monkey and a million years ago or did the monkey see

million years ago or did the monkey see

million years ago or did the monkey see a forest so we took the first image you

a forest so we took the first image you

a forest so we took the first image you take some very tiny patches from the

take some very tiny patches from the

take some very tiny patches from the forest and you do some statistical

forest and you do some statistical

forest and you do some statistical mathematics what is the best basis for

mathematics what is the best basis for

mathematics what is the best basis for all these patches and you find exactly

all these patches and you find exactly

all these patches and you find exactly the same filters so you can learn the

the same filters so you can learn the

the same filters so you can learn the filters from the data and that’s exactly

filters from the data and that’s exactly

filters from the data and that’s exactly what we do so I said suppose I’m an

what we do so I said suppose I’m an

what we do so I said suppose I’m an animal and I live in a restricted world

animal and I live in a restricted world

animal and I live in a restricted world I have only vertical lines it turns out

I have only vertical lines it turns out

I have only vertical lines it turns out that I’ll you got very specific filters

that I’ll you got very specific filters

that I’ll you got very specific filters restricted filters so nothing happens if

restricted filters so nothing happens if

restricted filters so nothing happens if I go up done but the lot happens in this

I go up done but the lot happens in this

I go up done but the lot happens in this direction so I

direction so I

direction so I the right filter so the lesson is that

the right filter so the lesson is that

the right filter so the lesson is that handcrafted filters are out for many

handcrafted filters are out for many

handcrafted filters are out for many many years me and all my colleagues we

many years me and all my colleagues we

many years me and all my colleagues we worked with let’s design a lot of

worked with let’s design a lot of

worked with let’s design a lot of filters and do pattern recognition and

filters and do pattern recognition and

filters and do pattern recognition and so on that’s over we learn them from the

so on that’s over we learn them from the

so on that’s over we learn them from the data we regulate the visual environment

data we regulate the visual environment

data we regulate the visual environment by keeping kittens in complete darkness

by keeping kittens in complete darkness

by keeping kittens in complete darkness from birth this is an experimental kit

from birth this is an experimental kit

from birth this is an experimental kit for periods of controlled visual

for periods of controlled visual

for periods of controlled visual experience inside special special

experience inside special special

experience inside special special cylindrical chambers this kitten

cylindrical chambers this kitten

cylindrical chambers this kitten they did the experiments on how was it

they did the experiments on how was it

they did the experiments on how was it formed after birth so the kitten was

formed after birth so the kitten was

formed after birth so the kitten was raised in the dark and for three months

raised in the dark and for three months

raised in the dark and for three months the only thing it could see was the same

the only thing it could see was the same

the only thing it could see was the same as I did with the trees horizontal lines

as I did with the trees horizontal lines

as I did with the trees horizontal lines can you turn off the sound from the next

can you turn off the sound from the next

can you turn off the sound from the next slide because let’s now see what the

slide because let’s now see what the

slide because let’s now see what the kitten has seen if the kitten sees a

kitten has seen if the kitten sees a

kitten has seen if the kitten sees a horizontal stick it perfectly sees the

horizontal stick it perfectly sees the

horizontal stick it perfectly sees the horizontal stick and of course you

horizontal stick and of course you

horizontal stick and of course you expect it if there’s a vertical stick it

expect it if there’s a vertical stick it

expect it if there’s a vertical stick it has no filters in its brain to see a

has no filters in its brain to see a

has no filters in its brain to see a vertical stick it cannot see it anymore

vertical stick it cannot see it anymore

vertical stick it cannot see it anymore so that’s quite striking this is what

so that’s quite striking this is what

so that’s quite striking this is what biology does this is what’s called brain

biology does this is what’s called brain

biology does this is what’s called brain plasticity adaptivity we learn from what

plasticity adaptivity we learn from what

plasticity adaptivity we learn from what we see well of course this kitten went

we see well of course this kitten went

we see well of course this kitten went to the family again and after that it’s

to the family again and after that it’s

to the family again and after that it’s a fully learnt it it’s all these things

the images that we see most are faces

the images that we see most are faces and you know you look the whole day at

and you know you look the whole day at

and you know you look the whole day at faces Facebook the way it even turns out

faces Facebook the way it even turns out

faces Facebook the way it even turns out that they have now found it in all kinds

that they have now found it in all kinds

that they have now found it in all kinds of experiments that we have a dedicated

of experiments that we have a dedicated

of experiments that we have a dedicated area in the brain that is just

area in the brain that is just

area in the brain that is just specifically meant for faces it only

specifically meant for faces it only

specifically meant for faces it only reacts on faces you give it anything

reacts on faces you give it anything

reacts on faces you give it anything else it doesn’t react but there’s a face

else it doesn’t react but there’s a face

else it doesn’t react but there’s a face but there it goes I wish he faces now

but there it goes I wish he faces now

but there it goes I wish he faces now everywhere even in the most stupid

everywhere even in the most stupid

everywhere even in the most stupid things we see faces so and why is this

things we see faces so and why is this

things we see faces so and why is this you look at Facebook the whole time but

you look at Facebook the whole time but

you look at Facebook the whole time but it’s one thing you don’t see and just

it’s one thing you don’t see and just

it’s one thing you don’t see and just just like the kitten the face upside

just like the kitten the face upside

just like the kitten the face upside down you have never seen so you don’t

down you have never seen so you don’t

down you have never seen so you don’t recognize it you have the same as the

recognize it you have the same as the

recognize it you have the same as the kitten even if you see a picture of a

kitten even if you see a picture of a

kitten even if you see a picture of a well-known person your mother whoever

well-known person your mother whoever

well-known person your mother whoever it’s upside down you have to look a

it’s upside down you have to look a

it’s upside down you have to look a second longer because we have no trains

second longer because we have no trains

second longer because we have no trains regions for faces upside down okay let’s

regions for faces upside down okay let’s

regions for faces upside down okay let’s go to some applications of all this what

go to some applications of all this what

go to some applications of all this what we learned especially with this deep

we learned especially with this deep

we learned especially with this deep learning one of the big breakthroughs is

learning one of the big breakthroughs is

learning one of the big breakthroughs is of course the self-driving car until it

of course the self-driving car until it

of course the self-driving car until it is very active in this area and why is

is very active in this area and why is

is very active in this area and why is it actually now becoming possible we

it actually now becoming possible we

it actually now becoming possible we have already cars that drove a million

have already cars that drove a million

have already cars that drove a million kilometers because they need to see

kilometers because they need to see

kilometers because they need to see passengers traffic signs all the

passengers traffic signs all the

passengers traffic signs all the different things and this deep learning

different things and this deep learning

different things and this deep learning this recognition

this recognition

this recognition you remember 96% is okay is that really

you remember 96% is okay is that really

you remember 96% is okay is that really working so it’s feasible it’s coming

working so it’s feasible it’s coming

working so it’s feasible it’s coming right there we have in Holland the

right there we have in Holland the

right there we have in Holland the largest flower production in the world I

largest flower production in the world I

largest flower production in the world I think we make about 40% of all the

think we make about 40% of all the

think we make about 40% of all the flowers nine billion roses every year

flowers nine billion roses every year

flowers nine billion roses every year and it’s the we have 450 roses some are

and it’s the we have 450 roses some are

and it’s the we have 450 roses some are very expensive is the right throws on

very expensive is the right throws on

very expensive is the right throws on the pallets does the farmer say okay

the pallets does the farmer say okay

the pallets does the farmer say okay that’s the expensive rose or is it an

that’s the expensive rose or is it an

that’s the expensive rose or is it an cheap one so we have now computer

cheap one so we have now computer

cheap one so we have now computer systems who check everything

systems who check everything

systems who check everything and my own field is medical imaging

and my own field is medical imaging

and my own field is medical imaging that’s a huge area it big

that’s a huge area it big

that’s a huge area it big 80% of all the diagnosis is done on

80% of all the diagnosis is done on

80% of all the diagnosis is done on images and if you make images you make a

images and if you make images you make a

images and if you make images you make a CT scan you easily make 1,000 slices so

CT scan you easily make 1,000 slices so

CT scan you easily make 1,000 slices so which doctor is going to look at 1,000

which doctor is going to look at 1,000

which doctor is going to look at 1,000 slices the doctor needs to be helped by

slices the doctor needs to be helped by

slices the doctor needs to be helped by these deep learning pattern recognition

these deep learning pattern recognition

these deep learning pattern recognition systems and they work they do an

systems and they work they do an

systems and they work they do an incredible job he I’m project Leda now

incredible job he I’m project Leda now

incredible job he I’m project Leda now of a large screening program that’s

of a large screening program that’s

of a large screening program that’s preventive medicine for diabetes and

preventive medicine for diabetes and

preventive medicine for diabetes and with diabetes your blood vessels start

with diabetes your blood vessels start

with diabetes your blood vessels start to leak you can’t see them you can’t put

to leak you can’t see them you can’t put

to leak you can’t see them you can’t put everyone in an MRI scan many people may

everyone in an MRI scan many people may

everyone in an MRI scan many people may have diabetes but they don’t know but

have diabetes but they don’t know but

have diabetes but they don’t know but your retina your eye you can see that

your retina your eye you can see that

your retina your eye you can see that very well and there you can see with the

very well and there you can see with the

very well and there you can see with the incredible resolution you can see the

incredible resolution you can see the

incredible resolution you can see the blood vessels and in China they have an

blood vessels and in China they have an

blood vessels and in China they have an enormous problem which that I be this

enormous problem which that I be this

enormous problem which that I be this 11.6% so our university is oval

11.6% so our university is oval

11.6% so our university is oval university is asked can you help with

university is asked can you help with

university is asked can you help with this huge problem and finds in our

this huge problem and finds in our

this huge problem and finds in our population who has doubled the amount of

population who has doubled the amount of

population who has doubled the amount of diabetes from elsewhere to find them so

diabetes from elsewhere to find them so

diabetes from elsewhere to find them so we’re now running a program finally we

we’re now running a program finally we

we’re now running a program finally we hope to screen 24 million people and our

hope to screen 24 million people and our

hope to screen 24 million people and our software can now automatically detect

software can now automatically detect

software can now automatically detect the beginnings of small leakages and so

the beginnings of small leakages and so

the beginnings of small leakages and so on and all things of course prevent

on and all things of course prevent

on and all things of course prevent blindness solace concludes the brain

blindness solace concludes the brain

blindness solace concludes the brain it’s our next revolution actually we

it’s our next revolution actually we

it’s our next revolution actually we have just started we know nothing yet

have just started we know nothing yet

have just started we know nothing yet about the brain we begin to see it but

about the brain we begin to see it but

about the brain we begin to see it but we had a major leap a couple of years

we had a major leap a couple of years

we had a major leap a couple of years ago the disruptive change because of

ago the disruptive change because of

ago the disruptive change because of these deep neural networks we will see

these deep neural networks we will see

these deep neural networks we will see this everywhere now it’s coming up

this everywhere now it’s coming up

this everywhere now it’s coming up radiologists are going to use it

radiologists are going to use it

radiologists are going to use it everyone who use computer inspection

everyone who use computer inspection

everyone who use computer inspection will use it and so on it will be one of

will use it and so on it will be one of

will use it and so on it will be one of the major descriptives so you saw some

the major descriptives so you saw some

the major descriptives so you saw some examples and actually now we have a

examples and actually now we have a

examples and actually now we have a little bit better understanding them

little bit better understanding them

little bit better understanding them were the creativity were it’s all

were the creativity were it’s all

were the creativity were it’s all emerges it’s in our brain our light bulb

emerges it’s in our brain our light bulb

emerges it’s in our brain our light bulb thank you very much

thank you very much

thank you very much you

you

you [Applause]

[Applause]

[Applause] [Music]

”

Be First to Comment

Leave a Reply

Your email address will not be published. Required fields are marked *