Theory of Visual Learning

runmidgeΤεχνίτη Νοημοσύνη και Ρομποτική

20 Οκτ 2013 (πριν από 3 χρόνια και 7 μήνες)

90 εμφανίσεις

Towards an
Implementation of a
Theory of Visual Learning
in the Brain

Shamit Patel

CMSC 601

May 2, 2011

The Problem


To develop a working theory of
learning in the human
neocortex

and implement it in software


Goal is for the learning algorithm
to match or exceed human
-
level
accuracy in visual pattern
recognition and other hierarchical
inference tasks

Hypothesis


My hypothesis is that the brain
learns through a feedback loop of
sensing and reacting. I call this
theory
SensoReaction
.


The brain essentially learns
through experience


Feedback is the crucial ingredient
of intelligence because it allows
the brain to refine its predictions
into the correct answer

Motivation


Medical image processing


Quality control


Surveillance


Ultimately, we would like to build
machines that operate on the
same
neurocomputational

mechanisms as the human brain

From Von Neumann Architecture
to Neural Architecture of the Brain

Image source:
http://
en.wikipedia.org/wiki/File:Von_Neumann_ar
chitecture.svg

Image source:
http://bluebrain.epfl.ch/files/content/sites/bluebrain
/files/bluebrain
-
neuron.jpg

Related Work


Numenta’s

Hierarchical Temporal
Memory (HTM) model


Riesenhuber

and
Poggio’s

HMAX
model


Fukushima’s
Neocognitron

model

The Human
Neocortex

Image source: http://www.ncbi.nlm.nih.gov/books/NBK10870/bin/ch26f3.jpg

Hierarchical Temporal Memory

Image source: http://upload.wikimedia.org/wikipedia/en/8/87/HTM_Hierarchy_example.png

Hierarchical Temporal Memory


Directly based on the structure
and computational properties of
the human
neocortex

[1]


Four main tasks of HTM: learning,
inference, prediction, and
behavior [1]


Strength: Efficiency due to
hierarchical structure [1]


Weakness: Needs lots of training
data

HMAX

Image source: http://
riesenhuberlab.neuro.georgetown.edu/hmaxSchemeCD.jpg

HMAX


Models the behavior of the ventral
visual stream [2]


Fundamental operations: (1) Weighted
linear sum for aggregating simple
features into complex ones, (2) Highly
nonlinear “MAX” operation that
computes output based on most active
input [2]


Strengths: Efficiency and invariance to
position and size of input pattern [2]


Weakness: Poor generalization to
objects of different classes [2]

Neocognitron

Image source: http://www.scholarpedia.org/wiki/images/9/9d/ScholarFig1.gif

Neocognitron


Self
-
organized via unsupervised
learning [3]


S
-
cells are changeable and C
-
cells
are invariant to position, shape,
and size of input pattern [3]


Strength: Unsupervised learning
means we don’t need labeled
data


Weakness: Poor generalization to
objects of different classes


Approach

1)
Implementation of HTM system

2)
Integration of
SensoReaction

algorithm
into the HTM system

3)
Training the HTM system on temporal
image data

4)
Testing the HTM system on novel input
patterns

5)
Statistical analysis of results


Implementation of HTM system


I have already implemented a
considerable part of the HTM
system, including the overall
structure of the network and
most of the training functionality


Remaining work consists of
implementing inference and
integrating
SensoReaction

into
the system

Integration of
SensoReaction

algorithm into HTM system


SensoReaction

is a feedback propagation
mechanism that allows predictions to be
propagated down the hierarchy for correction


Algorithm will be integrated into the HTM
system by first introducing feedback
connections between every pair of successive
layers in the network. Then, predictions will
be passed down the hierarchy via these
feedback connections.

Training the HTM system


Present hundreds of streams of temporal
image data to the input layer


Allow the system to build its internal
representations


Training will consist of: (1) memorizing
patterns, (2) building the Markov graphs, and
(3) forming the temporal groups

Evaluation/Testing the HTM system


Present thousands of noisy input
patterns to the HTM network


Observe the classification
accuracy of the HTM system


SensoReaction

algorithm comes
into play here by making
predictions, passing them down
the hierarchy, correcting them,
and passing them back up

Statistical Analysis of Results


Classification accuracy of HTM
system with
SensoReaction

will
be compared with classification
accuracy of standard HTM system


Two
-
sample
t
-
test will be used to
compare the classification
accuracies of the two systems

Feasibility of Approach


SensoReaction

is feasible because
it is essentially based on how the
neocortex

processes feedback


Feedback can only improve the
classification accuracy because
prior experience is taken into
account

Conclusion


Feedback is the critical piece of
intelligence


Brain learns through constant
sensing and reacting


Ultimate goal is to build machines
that work on the same
computational principles as the
brain



References


[1]
Numenta
, Inc. (2010,
December 10). Hierarchical
Temporal Memory including HTM
cortical learning algorithms
(Version No. 0.2). Retrieved from
http://
www.numenta.com/htm
-
overview/education/HTM
CorticalLearningAlgorithms.pdf

References


[2]
Riesenhuber
, M., &
Poggio
, T.
(1999, November). Hierarchical
models of object recognition in
cortex. Nature America, 2(11),
1019
-
1025. Retrieved from
http://cbcl.mit.edu/publications/
ps/nn99.pdf

References


[3] Fukushima, K. (1980).
Neocognitron
: a
self
-
organizing neural network model for a
mechanism of pat
-

tern recognition
unaffected by shift in position. Biological
Cybernetics, 36, 193
-
202. Retrieved from
http://lrn.no
-
ip.info/other/books/neural/Neocognitron/19
80 Neocognitron%20A%20Self
-
organizing
%20Neural%20Network%20Model%20for%2
0a%20Mechanism%20of%20Pattern%20Reco
gnition%20
Unaffected%20by%20Shift%20in%20Position.
pdf

Questions?