class 21, 1999 cbcl/ai mit neuroscience ii t. poggio

62
Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Upload: dayna-brittany-anderson

Post on 13-Dec-2015

222 views

Category:

Documents


3 download

TRANSCRIPT

Page 1: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Neuroscience II

T. Poggio

Page 2: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Neuroscience

Brain Overview?

Page 3: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

The Ventral Visual Pathway

modified from Ungerleider and Haxby, 1994

Page 4: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Page 5: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Visual Areas

Page 6: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Face-tuned cells in IT

Page 7: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Model of view-invariant recognition: learning from views

VIEW ANGLE

Poggio, Edelman Nature, 1990.

A graphical rewriting of mathematics of regularization (GRBF),a learning technique

Page 8: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Learning to Recognize3D Objects in IT Cortex

Logothetis, Pauls, Poggio1995

Examples of Visual Stimuli

After human psychophysics (Buelthoff, Edelman,Tarr, Sinha,…), whichsupports modelsbased on view-tunedunits...physiology!

Page 9: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Task Description

Task Description

Lef t LeverBlue Fixspot

Response

Color Change

2 sec

Stimulus

Yellow Fixspot

Response

OffOn

Recognition Task

Fixation Task

StimulusRight Lever

T TTT TD DD DDTT = TargetD = Distractor

Testing P haseLear ning Phase

Stimulus

Blue Fixspot

Response

Stimulus

Yellow Fixspot

Response

Left Lever

Right Lever

T = TargetD = Distractor

Logothetis, Pauls, Poggio1995

Page 10: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Recording Sites in Anterior IT

LUNLAT

IOS

STS

AMTSLAT

STS

AMTS

Ho=0

Logothetis, Pauls, and Poggio, 1995;Logothetis, Pauls, 1995

Page 11: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Model’s predictions: View-tuned Neurons

VIEW ANGLE

VIEW-TUNEDUNITS

Page 12: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

The Cortex: Neurons Tuned to Object Views

Logothetis, Pauls, Poggio1995

Page 13: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

A View Tuned Cell

12 7224 8448 10860 12036 96

12 24 36 48 60 72 84 96 108 120 132 168o o o o o o o o o o o o

-108 -96 -84 -72 -60 -48 -36 -24 -12 0-168 -120

Distractors

Target Views60

sp

ikes

/sec

800 msec

-108 -96 -84 -72 -60 -48 -36 -24 -12 0-168 -120 oo o o o o o o o oo o

Logothetis, Pauls, Poggio1995

Page 14: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Model’s predictions : View-invariant, Object-specific

Neurons

View Angle

VIEW-INVARIANT,

OBJECT-SPECIFIC

UNIT

Page 15: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

The Cortex: View-invariant, Object-specific Neurons

Logothetis, Pauls, Poggio,1995

Page 16: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Recognition of Wire Objects

Page 17: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Generalization Field

Distractors (N=60)

10

0

Z

Y

X

- +45

Y

+45

-45

X

45

5

10

15

20

25

90

45

0

-45

-90-90

-450

4590

Page 18: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

600 msec

1 2 3 4 6

7 8 9 10 12

13 14 15 16 18

20 21 22 28 30

184 s

pik

es/s

ec

Amoeba 01, Cell = 265

(a)

(b)

48 o

96 o

144 o

0 o

60 o

108o

156 o

12 o

72 o

120o

168 o

24 o

36 o

84 o

-12 o

132 o

Page 19: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Wire 526, Cell = 202

(b)

(a)

o108

o60

o12

-36o

o84

o36

o

-60 o

-12

o72

o24

o

-72 o

-24

o96

o48

-48 o

o0

14

2 sp

ike

s/se

c

600 msec

4

22

39

17

5

24

43

18

25

44

8

45

49

26

20

9

27

50

59

21

Page 20: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Distractors (N=60)0

10

Spik

es p

er

Second

-180 -135 -90 -45 0 45 90 135 1800

16

32

48

64

80 ( - 120 deg) ( 60 deg)

Rotation Around Y Axis

0

5

10

15

20

25

0 60 120 180-60-120-180S

pik

es p

er

Second

Rotation Around Y Axis

Hit Rate > 95% for all views

Page 21: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

View-dependent Response of an IT Neuron

0 250 500 0 250 500 0 250 500 0 250 500 0 250 500 0 250 500 0 250 500

160

Hit

Ra

te

0

2040

60

80100

Sp

ike

s p

er S

eco

nd

10

20

30

40

50

60

0 60 120 180-60-120-180

0

-160 -120 -40 60 120900

Rotation Around Y Axis (degrees)0 60 120 180-60-120-180

Page 22: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Sparse Representations in IT

• About 400 view tuned cells per object

• Perhaps 20 view-invariant cells per object

In the recording area in AMTS -- a In the recording area in AMTS -- a specialized region for paperclips (!) --specialized region for paperclips (!) --we estimate that there are, after training,we estimate that there are, after training, (within an order of magnitude or two) …

Logothetis, Pauls, Poggio, 1997

Page 23: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Previous glimpses: cells tuned to face identity and

view

Perrett, 1989

Page 24: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

2. View-tuned IT neurons

View-tuned cells in

IT Cortex:

how do they work?

How do they

achieve selectivity

and invariance? Max Riesenhuber andT. Poggio, Nature Neuroscience, just published

Page 25: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

max

Some ofour fundingis fromHonda...

Page 26: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Model’s View-tuned Neurons

VIEW ANGLE

VIEW-TUNEDUNITS

Page 27: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Scale-Invariant Responses of an IT Neuron

(training on one size only!)

Logothetis, Pauls and Poggio, 1995

Scale Invariant Responses of an IT Neuron

0 2000 3000Time (msec)

1000

Spi

kes/

sec

0

76

0 2000 3000Time (msec)

1000

Spi

kes/

sec

0

76

0 2000 3000Time (msec)

1000

Spi

kes/

sec

0

76

0 2000 3000Time (msec)

1000

Spi

kes/

sec

0

76

0 2000 3000Time (msec)

1000

Spi

kes/

sec

0

76

0 2000 3000Time (msec)

1000

Spi

kes/

sec

0

76

0 2000 3000Time (msec)

1000

Spi

kes/

sec

0

76

0 2000 3000Time (msec)

1000

Spi

kes/

sec

0

76

4.0 deg(x 1.6)

4.75 deg(x 1.9)

5.5 deg(x 2.2)

6.25 deg(x 2.5)

2.5 deg(x 1.0)

1.0 deg(x 0.4)

1.75 deg(x 0.7)

3.25 deg(x 1.3)

Scale Invariant Responses of an IT Neuron

Page 28: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

• Invariance around training view

• Invariance while maintaining specificity

*

Sp

ike

R

ate

Distractor ID

10 Best Distractors

37 9 20 5 24 3 2 1 0 6

0

10

20

30

40

60 108 132 156 18084

0

10

20

30

40

Rotation Around Y Axis

(a) (b)

Azimuth and Elevation(x = 2.25 degrees)

1.90 2.80 3.70 4.70 5.60

0

1

2

3

4

5

6

7

( 0,0) ( x,x) ( x,- x)( - x,x) ( - x,- x)

0

1

2

3

4

5

6

Degrees of Visual Angle(Target Response)/

(M

ea

n o

f B

est D

istra

cto

rs)

(c) (d)

Sp

ike

Ra

te(T

arg

et

Re

spo

nse

)/(M

ea

n o

f B

est

Dis

tra

cto

rs)

Invariances: Overview

Logothetis, Pauls and Poggio, 1995

Page 29: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Our quantitative model builds upon previous hierarchical models

•Hubel & Wiesel (1962): Simple to complex to ``higher order

hypercomplex cells’’

•Fukushima (1980): Alternation of “S” and “C” layers to build up

feature specificity and translation invariance, resp.

•Perrett & Oram (1993): Pooling as general mechanism to achieve

invariance

Page 30: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Model of view tuned cells

MAX Riesenhuber andTommy Poggio, 1999

Page 31: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Model Diagram

“IT”

“V4”

“V1”

. . .

...

. . .

...

w

View-specific learning: synaptic plasticity

Page 32: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Max (or “softmax”)

• key mechanism in the model

• computationally equivalent to selection (and scanning in our object detection system)

Page 33: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

V1: Simple Features, Small Receptive Fields

• Simple cells respond to bars

Hubel & Wiesel, 1959•“Complex Cells”: translation invariance; pool over simple cells of the same orientation (Hubel&Wiesel)

Page 34: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Two possible Pooling Mechanisms

thanks to Pawan Sinha

Nn

nn

Page 35: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

An Example: Simple to Complex Cells

“simple”cells

“complex” cell

?

Page 36: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Simple to Complex: Invariance to Position and Feature

Selectivity

?

“simple”cells

“complex” cell

Page 37: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

3. Some predictions of the model

• Scale and translation invariance of view-tuned AIT neurons

• Response to pseudomirror views

• Effect of scrambling

• Multiple objects

• Robustness to clutter

• Consistent with K. Tanaka’s simplification procedure

• More and more complex features from V1 to AIT

Page 38: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Testing Selectivity and Invariance of Model Neurons

• Test specificity AND transformation tolerance of view-tuned model neurons

• Same objects as in Logothetis’ experiment

• 60 distractors

Page 39: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Invariances of IT (view-tuned) Model Neuron

Page 40: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Invariances: Experiment vs. Model (view-tuned cells)

05

10152025303540

3D Rotation

degrees

0

0.5

1

1.5

2

2.5

translation

degrees o

f v

is. angle

0

0.5

1

1.5

2

2.5

3

3.5

scale change

octaves

Model

Experiment

*

Page 41: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

MAX vs. Summation

05

10152025303540

3D Rotation

deg

rees

0

0.5

1

1.5

2

translation

deg

rees o

f v

is. a

ng

le

0

0.5

1

1.5

2

2.5

3

3.5

scale change

octaves

max sum

Page 42: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Response toPseudo-Mirror Views

As in experiment, somemodel neurons show tuningto pseudo-mirror image

Page 43: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Robustness to scrambling: model and IT neurons

Experiments: Vogels, 1999

Page 44: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Recognition in Context: Two Objects

Page 45: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Recognition in Context: some experimental support

• Sato: Response of IT cells to two stimuli in RF

Sato, 1989

Page 46: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Recognition in Clutter:data

How does response of IT neurons change if background is introduced?

00.30.60.91.2

avg.

re

spon

se

stimulus stim + bg

00.250.5

0.751

%

CO

RREC

T

stimulus stim + bg

Missal et al., 1997

Page 47: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Recognition in Clutter: model

• average model neuron response

• recognition rates

Page 48: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Further Support: Keiji just mentioned his simplification paradigm...

Wang et al., 1998

Page 49: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Consistent behaviour of the model

Page 50: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Higher complexity and invariances in Higher Areas

Kobatake & Tanaka, 1994

Page 51: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Fujita and Tanaka’s Dictionary of Shapes (about 3000) in posterior IT (columnar

organization)

Page 52: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Similar properties in the model...

M. Tarr, Nature Neuroscience

Page 53: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Layers With Linear Pooling and With Max Pooling

•Linear pooling: yields more complex features (e.g. from LGN

inputs to simple cells and -- perhaps -- from PIT to AIT cells)

•Max pooling: yields invariant (position, scale) features

over a larger receptive field(e.g. from simple to complex V1 cells)

Page 54: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

4. Hypothetical circuitry for Softmax

• The max operation is at the core of the model properties

• Which biophysical mechanisms and circuitry underlies the max operation?

Page 55: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Softmax circuitry

The SOFTMAX operation may arise from cortical microcircuitsof lateral inhibition between neurons in a cortical layer. An example:a circuit based on feed forward (or recurrent) shunting presynaptic (or post synaptic) inhibition. Key elements: 1) shunting inhibition 2) nonlinear transformation of the signals (synaptic nonlinearities or active membrane properties). The circuit performs: a gain control operation (as in the canonical microcircuit of Martin and Douglas…) and -- for certain values of the parameters -- a softmax operation:

j

pj

qi

i x

xy

Page 56: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Summary: main points of model

• Max-like operation, computationally similar to scanning and

selecting • Hypothetical inhibitory microcircuit for Softmax in cortex • Easy grafting of top-down attentional effect on circuitry• Segmentation is a byproduct of recognition• No binding problem, syncrhonization not needed• Model is extension of classical hierarchical H-W scheme• Model deals with nice object classes (e.g. faces) and can be extended to object classification (rather then subordinate level recognition).

• Just a plausibility proof!• Experiments wanted (to prove it wrong)!

Page 57: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Category boundary

Prototypes

100% Cat

80% Cat Morphs

60% Cat Morphs

60% Dog Morphs 80% Dog

Morphs

Prototypes 100% Dog

Novel 3D morphing system to create new objects that are linear combinations of 3D prototypes

Page 58: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

.. .

.

..

.

FixationSample

Delay

Test(Nonmatch)

Delay

(Match)

Test(Match)

600 ms.

1000 ms.

500 ms.

Object classification task for monkey physiology

Page 59: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

dog 100%

dog 80%dog 60%

cat 60%cat 80%

cat 100%

0 500 1000 1500 2000 2500 300010

15

20

25

30

35

40

45l04.spk 1301

time (msec)

spik

e ra

te (

Hz)

Dog activity

Cat activity

Sample on Delay period Fixation

Preliminary results from Prefrontal Cortex Recordings

This suggests that prefrontal neurons carry information about the category of objects

Page 60: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Page 61: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Recognition in Context: some experimental support

• Sato: Response of IT cells to two stimuli in RF

Sato, 1989

Summation index

for Max is 0for Sum is 1

Sato finds -0.1 in the average

Page 62: Class 21, 1999 CBCl/AI MIT Neuroscience II T. Poggio

Class 21, 1999

CBCl/AI MIT

Simulation