Pattern Recognition as an Internalized Motor Programme

A new conceptual architecture for low-level neural pattern recognition is presented. The key ideas are that the brain implements support vector machines and that support vectors are represented as memory patterns in competitive queuing memories. A binary classifier is built from two competitive queuing memories holding positive and negative valence training examples respectively. The support vector machine classification function is calculated in synchronized evaluation cycles. The kernel is computed by bisymmetric feed-forward networks feed by sensory input and by competitive queuing memories traversing the complete sequence of support vectors. Temporary summation generates the output classification. It is speculated that perception apparatus in the brain reuses structures that have evolved for enabling fluent execution of prepared action sequences so that pattern recognition is built on internalized motor programmes.

Authors:

• M. Jändel

Keywords:

• Competitive queuing model
• Olfactory system
• Pattern recognition
• Support vector machine
• Thalamus

References:

[1] T. Teyke, "Food-attraction conditioning in the snail, Helix Pomatia.," J.
Comp. Physiol, vol. A 177, pp. 409-414, 1995.
[2] F. Macrides, H. B. Eichenbaum, and W. B. Forbes, "Temporal
relationship between sniffing and the limbic ╬©´Çá-rhythm during odor
discrimination reversal learning," J. Neurosci., vol. 2, pp. 1705-1717,
1982.
[3] M. Jändel, "A neural support vector machine," Neural Networks, vol. 23,
pp. 607-613, 2010.
[4] M. Jändel, "Thalamic bursts mediate pattern recognition," in Proc. 4th
International IEEE EMBS Conf. on Neural Engineering, 2009, pp. 562-
565.
[5] M. Jändel, "Evolutionary path to biological kernel machines," in Proc.
of Brain Inspired Cognitive Systems, 2010, to be published.
[6] J. Elman, "Language processing," in The Handbook Of Brain Theory
And Neural Networks, M. Arbib, Ed. MIT Press, 1995, pp. 508-512.
[7] P. F. Dominey, "Influences of temporal organization on sequence
learning and transfer," J. Exp. Psychol. Learn. Mem. Cogn., vol. 24, pp.
234-248, 1998.
[8] J. L. Elman, "Finding structure in time," Cognitive Science, vol. 14, pp.
179-211, 1990.
[9] S. Grossberg, "A theory of human memory: Self-organization and
performance of sensory-motor codes, maps, and plans," in Progress in
Theoretical Biology, vol. 5, R. Rosen, and F. Snell, Eds. Academic
Press, 1978, pp. 233-374.
[10] G. Houghton, "The problem of serial order: A neural network
model of sequence learning and recall," in Current Research In Natural
Language Generation, R. Dale et al, Eds. Academic Press, 1990, pp.
287-319.
[11] D. Bullock, and B. Rhodes, "Competitive queuing for serial
planning and performance," in Handbook of Brain Theory And Neural
Networks, M. Arbib, Ed. MIT Press, 2003, pp. 241-244.
[12] D. Bullock, "Adaptive neural models of queuing and timing in fluent
action," Trends in Cognitive Sciences, vol. 8, no. 9, pp. 426-433, 2004.
[13] I. Boardman, and D. Bullock, "A neural network model of serial order
recall from short-term memory," in Proceedings of the International
Joint Conference on Neural Networks, II, pp. 879-884, 1991.
[14] G. Bradski, G. A. Carpenter, and S. Grossberg, "STORE working
memory networks for storage and recall of arbitrary temporal
sequences," Biol. Cybern., vol. 71, pp. 469-480, 1994.
[15] B. Rhodes, and D. Bullock, "Neural dynamics of learning and
performance of fixed sequences: Latency pattern reorganizations and the
N-STREAMS model," Boston University Technical Report CAS/CNS-
02-007, 2002.
[16] B. B. Averbeck, M. V. Chafee, D. A. Crowe, and A. P. Georgopoulos,
"Parallel processing of serial movements in prefrontal cortex," Proc. Natl.
Acad. Sci. U. S. A., vol. 99, pp. 13172-13177, 2002.
[17] N. Cristianini, and J. Shawe-Taylor, An introduction to support vector
machines and other kernel-based methods. Cambridge: Cambridge
University Press, 2000.
[18] B. Schölkopf, A. J. Smola, R. C. Williamson, and P. L. Bartlett, "New
support vector algorithms," Neural Computation, vol. 12, pp. 1207-
1245, 2000.
[19] C-C. Chang, and C-J. Lin, "Training Λ-support vector classifiers: theory
and algorithms," Neural Computation, vol. 13, pp. 2119-2147, 2001.
[20] M. F. Quintilianus, Institutio Oratoria, Book XI, 95 (English translation
in The Orators Education, vol. 5, books 11-12, Loeb classical library).
[21] B. Schölkopf, and A. J. Smola, Learning with kernels. Cambridge MA:
MIT Press, 2002.
[22] H. J. Caulfield, and K. Heidary, "Exploring margin setting for good
generalization in multiple class discrimination," Pattern Recognition,
vol. 38, pp. 1225-1238, 2005.
[23] S. M. Sherman, and R. W. Guillery, Exploring the thalamus and its role
in cortical function, 2nd ed., Cambridge, MA: MIT Press, 2006.
[24] A. D. Baddeley, Essentials of human memory. New York: Psychology
Press, 1999.
[25] L. B. Haberly, "Parallel-distributed processing in olfactory cortex: new
insights from morphological and physiological analysis of neuronal
circuitry," Chem. Senses, vol. 26, pp. 551-576, 2001.
[26] G. Cybenko, "Approximations by superpositions of a sigmoidal
function," Math. of Control, Signals and Syst., vol. 2, pp. 303-314,
1989.
[27] C. S. Ong, X. Mary, S. Canu, and A.J. Smola, "Learning with nonpositive
kernels," in Proc. of the 21st International Conference on
Machine Learning, 2004, pp. 81-89.
[28] B. Schölkopf, C. Burges, and V. Vapnik, "Extracting support data for a
given task," in Proc. First Annual Conference on Knowledge Discovery
& Data Mining, 1995, pp. 252-257.
[29] D. Johnston, and S.M-S. Wu, Foundations of cellular neurophysiology.
Cambridge MA: MIT Press, 1995.
[30] L. B. Haberly, "Olfactory cortex," in The synaptic organization of the
brain, 4th ed., G. M. Shepherd, Ed., Oxford: Oxford University Press,
1998, pp. 377-416.