Learning Temporally Persistent Hierarchical Representations

A biologically motivated model of cortical self-organization is proposed. Context is combined with bottom-up information via a maximum likelihood cost function. Clusters of one or more units are modulated by a common contextual gating Signal; they thereby organize themselves into mutually supportive predictors of abstract contextual features. The model was tested in its ability to discover viewpoint-invariant classes on a set of real image sequences of centered, gradually rotating faces. It performed considerably better than supervised back-propagation at generalizing to novel views from a small number of training examples.

[1]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[2]  James L. McClelland,et al.  An interactive activation model of context effects in letter perception: I. An account of basic findings. , 1981 .

[3]  R. von der Heydt,et al.  Illusory contours and cortical neuron responses. , 1984, Science.

[4]  P. C. Murphy,et al.  Corticofugal feedback influences the generation of length tuning in the visual pathway , 1987, Nature.

[5]  Steven J. Nowlan,et al.  Maximum Likelihood Competitive Learning , 1989, NIPS.

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

[7]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.

[8]  J. H. Neely.  Semantic priming effects in visual word recognition: A selective review of current findings and theories. , 1991 .

[9]  Suzanna Becker,et al.  Learning to Categorize Objects Using Temporal Coherence , 1992, NIPS.

[10]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[11]  Jim Kay,et al.  The discovery of structure by multi-stream networks of local processors with contextual guidance , 1995 .

[12]  James V. Stone.  Learning Perceptually Salient Visual Parameters Using Spatiotemporal Smoothness Constraints , 1996, Neural Computation.

[13]  William H. Calvin.  Cortical columns, modules, and Hebbian cell assemblies , 1998 .