Invariant object recognition in the visual system with error correction and temporal difference learning

It has been proposed that invariant pattern recognition might be implemented using a learning rule that utilizes a trace of previous neural activity which, given the spatio-temporal continuity of the statistics of sensory input, is likely to be about the same object though with differing transforms in the short time scale. Recently, it has been demonstrated that a modified Hebbian rule which incorporates a trace of previous activity but no contribution from the current activity can offer substantially improved performance. In this paper we show how this rule can be related to error correction rules, and explore a number of error correction rules that can be applied to and can produce good invariant pattern recognition. An explicit relationship to temporal difference learning is then demonstrated, and from this further learning rules related to temporal difference learning are developed. This relationship to temporal difference learning allows us to begin to exploit established analyses of temporal difference learning to provide a theoretical framework for better understanding the operation and convergence properties of these learning rules, and more generally, of rules useful for learning invariant representations. The efficacy of these different rules for invariant object recognition is compared using VisNet, a hierarchical competitive network model of the operation of the visual system.

[1]  Keiji Tanaka,et al.  Coding visual images of objects in the inferotemporal cortex of the macaque monkey. , 1991, Journal of neurophysiology.

[2]  E T Rolls,et al.  Sparseness of the neuronal representation of stimuli in the primate temporal visual cortex. , 1995, Journal of neurophysiology.

[3]  Bernard Widrow,et al.  Adaptive Signal Processing , 1985 .

[4]  Roland Baddeley,et al.  Optimal, Unsupervised Learning in Invariant Object Recognition , 1997, Neural Computation.

[5]  Guy M. Wallis,et al.  Using Spatio-temporal Correlations to Learn Invariant Object Recognition , 1996, Neural Networks.

[6]  Graeme Mitchison,et al.  Removing Time Variation with the Anti-Hebbian Differential Synapse , 1991, Neural Computation.

[7]  E. Rolls.  Functions of the Primate Temporal Lobe Cortical Visual Areas in Invariant Visual Object and Face Recognition , 2000, Neuron.

[8]  E. Rolls.  Learning mechanisms in the temporal lobe visual cortex , 1995, Behavioural Brain Research.

[9]  R. Desimone.  Face-Selective Cells in the Temporal Cortex of Monkeys , 1991, Journal of Cognitive Neuroscience.

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

[11]  M. Tovée,et al.  Processing speed in the cerebral cortex and the neurophysiology of visual masking , 1994, Proceedings of the Royal Society of London. Series B: Biological Sciences.

[12]  勇一 作村,et al.  Biophysics of Computation , 2001 .

[13]  Masao Ito.  The Cerebellum And Neural Control , 1984 .

[14]  Hanchuan Peng,et al.  Energy function for learning invariance in multilayer perceptron , 1998 .

[15]  E. Rolls.  Brain mechanisms for invariant visual recognition and learning , 1994, Behavioural Processes.

[16]  E T Rolls,et al.  Neurophysiological mechanisms underlying face processing within and beyond the temporal cortical visual areas. , 1992, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[17]  Peter Földiák,et al.  Learning Invariance from Transformation Sequences , 1991, Neural Comput..

[18]  M R DeWeese,et al.  How to measure the information gained from one symbol. , 1999, Network.

[19]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[20]  Edmund T. Rolls,et al.  A Model of Invariant Object Recognition in the Visual System: Learning Rules, Activation Functions, Lateral Inhibition, and Information-Based Performance Measures , 2000, Neural Computation.

[21]  G. Wallis,et al.  Learning invariant responses to the natural transformations of objects , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[22]  A G Barto,et al.  Toward a modern theory of adaptive networks: expectation and prediction. , 1981, Psychological review.

[23]  E. Rolls,et al.  View-invariant representations of familiar objects by neurons in the inferior temporal visual cortex. , 1998, Cerebral cortex.

[24]  E. Rolls,et al.  Neural networks and brain function , 1998 .

[25]  M. Ito,et al.  Long-term depression. , 1989, Annual review of neuroscience.

[26]  Andrew G. Barto,et al.  Reinforcement learning , 1998 .

[27]  A. Treves,et al.  The representational capacity of the distributed encoding of information provided by populations of neurons in primate temporal visual cortex , 1997, Experimental Brain Research.