+ All Categories
Home > Documents > Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2,...

Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2,...

Date post: 29-Mar-2015
Category:
Upload: tiana-ruscoe
View: 221 times
Download: 2 times
Share this document with a friend
Popular Tags:
25
Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011
Transcript
Page 1: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

Towards an Implementation of a

Theory of Visual Learning in the Brain

Shamit PatelCMSC 601

May 2, 2011

Page 2: 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

Page 3: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 4: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 5: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

From Von Neumann Architecture to Neural Architecture of the Brain

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

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

Page 6: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

Related Work

• Numenta’s Hierarchical Temporal Memory (HTM) model

• Riesenhuber and Poggio’s HMAX model

• Fukushima’s Neocognitron model

Page 7: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

The Human Neocortex

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

Page 8: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

Hierarchical Temporal Memory

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

Page 9: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 10: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

HMAX

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

Page 11: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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]

Page 12: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

Neocognitron

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

Page 13: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 14: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

Approach

1) Implementation of HTM system2) Integration of SensoReaction algorithm

into the HTM system3) Training the HTM system on temporal

image data4) Testing the HTM system on novel input

patterns5) Statistical analysis of results

Page 15: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 16: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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.

Page 17: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 18: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 19: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 20: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 21: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 22: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 23: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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

Page 24: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

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/1980 Neocognitron%20A%20Self-organizing %20Neural%20Network%20Model%20for%20a%20Mechanism%20of%20Pattern%20Recognition%20 Unaffected%20by%20Shift%20in%20Position.pdf

Page 25: Towards an Implementation of a Theory of Visual Learning in the Brain Shamit Patel CMSC 601 May 2, 2011.

Questions?


Recommended