Optimal, Unsupervised Learning in Invariant Object Recognition

A means for establishing transformation-invariant representations of objects is proposed and analyzed, in which different views are associated on the basis of the temporal order of the presentation of these views, as well as their spatial similarity. Assuming knowledge of the distribution of presentation times, an optimal linear learning rule is derived. Simulations of a competitive network trained on a character recognition task are then used to highlight the success of this learning rule in relation to simple Hebbian learning and to show that the theory can give accurate quantitative predictions for the optimal parameters for such networks.

[1]  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).

[2]  John S. Bridle,et al.  Training Stochastic Model Recognition Algorithms as Networks can Lead to Maximum Mutual Information Estimation of Parameters , 1989, NIPS.

[3]  E. Rolls,et al.  INVARIANT FACE AND OBJECT RECOGNITION IN THE VISUAL SYSTEM , 1997, Progress in Neurobiology.

[4]  Norbert Wiener,et al.  Extrapolation, Interpolation, and Smoothing of Stationary Time Series, with Engineering Applications , 1949 .

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

[6]  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.

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

[8]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

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

[10]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[11]  E. T. Jaynes,et al.  Papers on probability, statistics and statistical physics , 1983 .

[12]  Norbert Wiener,et al.  Extrapolation, Interpolation, and Smoothing of Stationary Time Series , 1964 .

[13]  Guy Wallis,et al.  Temporal Order in Human Object Recognition Learning , 1998 .

[14]  H H Bülthoff,et al.  Psychophysical support for a two-dimensional view interpolation theory of object recognition. , 1992, Proceedings of the National Academy of Sciences of the United States of America.

[15]  T. Poggio,et al.  A network that learns to recognize three-dimensional objects , 1990, Nature.

[16]  David I. Perrett,et al.  Neurophysiology of shape processing , 1993, Image Vis. Comput..

[17]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[18]  Y. Miyashita.  Neuronal correlate of visual associative long-term memory in the primate temporal cortex , 1988, Nature.

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

[20]  M. Tarr,et al.  Mental rotation and orientation-dependence in shape recognition , 1989, Cognitive Psychology.

[21]  Hanchuan Peng,et al.  Using sparse trace neural network to extract temporal-spatial invariance , 1998, 1998 IEEE International Joint Conference on Neural Networks Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36227).

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