A neural support vector machine

Support vector machines are state-of-the-art pattern recognition algorithms that are well founded in optimization and generalization theory but not obviously applicable to the brain. This paper presents Bio-SVM, a biologically feasible support vector machine. An unstable associative memory oscillates between support vectors and interacts with a feed-forward classification pathway. Kernel neurons blend support vectors and sensory input. Downstream temporal integration generates the classification. Instant learning of surprising events and off-line tuning of support vector weights trains the system. Emotion-based learning, forgetting trivia, sleep and brain oscillations are phenomena that agree with the Bio-SVM model. A mapping to the olfactory system is suggested.

[1]  K. Kaneko.  Clustering, coding, switching, hierarchical ordering, and control in a network of chaotic elements , 1990 .

[2]  Walter J. Freeman,et al.  Reafference and Attractors in the Olfactory System During Odor Recognition , 1996, Int. J. Neural Syst..

[3]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[4]  Bernhard Schölkopf,et al.  Learning with kernels , 2001 .

[5]  Donald O. Walter,et al.  Mass action in the nervous system , 1975 .

[6]  L. Abbott,et al.  Synaptic Depression and Cortical Gain Control , 1997, Science.

[7]  H. Markram,et al.  The neural code between neocortical pyramidal neurons depends on neurotransmitter release probability. , 1997, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Thomas A Cleland,et al.  Computation in the olfactory system. , 2005, Chemical senses.

[9]  A. Baddeley.  Essentials of Human Memory , 1999 .

[10]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[11]  G. Shepherd.  The Synaptic Organization of the Brain , 1979 .

[12]  Ichiro Tsuda,et al.  Towards an interpretation of dynamic neural activity in terms of chaotic dynamical systems , 2000 .

[13]  Carol M. Petito.  The Synaptic Organization of the Brain, 4th Ed , 1998 .

[14]  I. Tsuda.  Toward an interpretation of dynamic neural activity in terms of chaotic dynamical systems. , 2001, The Behavioral and brain sciences.

[15]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[16]  D. Johnston,et al.  Foundations of Cellular Neurophysiology , 1994 .

[17]  L. Haberly,et al.  Parallel-distributed processing in olfactory cortex: new insights from morphological and physiological analysis of neuronal circuitry. , 2001, Chemical senses.

[18]  Ichiro Tsuda,et al.  Dynamic link of memory--Chaotic memory map in nonequilibrium neural networks , 1992, Neural Networks.

[19]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[20]  Hilbert J. Kappen,et al.  Associative Memory with Dynamic Synapses , 2002, Neural Computation.

[21]  Robert Kozma,et al.  Chaotic Resonance - Methods and Applications for Robust Classification of noisy and Variable Patterns , 2001, Int. J. Bifurc. Chaos.

[22]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[23]  H. Eichenbaum,et al.  Temporal relationship between sniffing and the limbic theta rhythm during odor discrimination reversal learning , 1982, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[24]  Alexander J. Smola,et al.  Learning with non-positive kernels , 2004, ICML.

[25]  K. Ikeda,et al.  Maxwell-Bloch Turbulence , 1989 .

[26]  Kunihiko Kaneko,et al.  ISSUE : Chaotic Itinerancy Chaotic itinerancy , 2003 .

[27]  Gordon M. Shepherd,et al.  Olfactory cortex , 1998 .

[28]  Bernhard Schölkopf,et al.  New Support Vector Algorithms , 2000, Neural Computation.

[29]  Bernhard E. Boser,et al.  A training algorithm for optimal margin classifiers , 1992, COLT '92.

[30]  Chih-Jen Lin,et al.  Manuscript Number: 2187 Training ν-Support Vector Classifiers: Theory and Algorithms , 2022 .

[31]  Horn,et al.  Neural networks with dynamical thresholds. , 1989, Physical review. A, General physics.

[32]  Bernhard Schölkopf,et al.  Extracting Support Data for a Given Task , 1995, KDD.

[33]  I. Tsuda,et al.  A New Type of Self-Organization Associated with Chaotic Dynamics in Neural Networks , 1996, Int. J. Neural Syst..

[34]  Hans Liljenström,et al.  Neural Stability and Flexibility: A Computational Approach , 2003, Neuropsychopharmacology.

[35]  Zhaoping Li,et al.  Odour recognition and segmentation by a model olfactory bulb and cortex. , 2000 .

[36]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[37]  W. Freeman,et al.  How brains make chaos in order to make sense of the world , 1987, Behavioral and Brain Sciences.