Perceiving without Learning: From Spirals to Inside/Outside Relations

As a benchmark task, the spiral problem is well known in neural networks. Unlike previous work that emphasizes learning, we approach the problem from a generic perspective that does not involve learning. We point out that the spiral problem is intrinsically connected to the inside/ outside problem. A generic solution to both problems is proposed based on oscillatory correlation using a time delay network. Our simulation results are qualitatively consistent with human performance, and we interpret human limitations in terms of synchrony and time delays, both biologically plausible. As a special case, our network without time delays can always distinguish these figures regardless of shape, position, size, and orientation.

[1]  Stephen Grossberg,et al.  A neural network architecture for figure-ground separation of connected scenic figures , 1991, Neural Networks.

[2]  DeLiang Wang,et al.  Locally excitatory globally inhibitory oscillator networks , 1995, IEEE Transactions on Neural Networks.

[3]  DeLiang Wang,et al.  Modeling Global Synchrony in the Visual Cortex by Locally Coupled Neural Oscillators , 1994 .

[4]  J. I. Nelson,et al.  Binding in the visual system , 1998 .

[5]  Gerald Sommer,et al.  Dynamic Cell Structure Learns Perfectly Topology Preserving Map , 1995, Neural Computation.

[6]  P. Milner.  A model for visual shape recognition. , 1974, Psychological review.

[7]  Deliang Wang,et al.  Relaxation oscillators with time delay coupling , 1998 .

[8]  S. Ullman.  Visual routines , 1984, Cognition.

[9]  Christian Lebiere,et al.  The Cascade-Correlation Learning Architecture , 1989, NIPS.

[10]  W Singer,et al.  Visual feature integration and the temporal correlation hypothesis. , 1995, Annual review of neuroscience.

[11]  I P Howard,et al.  Proposals for the Study of Anomalous Perceptual Schemata , 1974, Perception.

[12]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[13]  Jian-Zhong Guo,et al.  Electrophysiological identification of horizontal synaptic connections in rat visual cortex in vitro , 1993, Neuroscience Letters.

[14]  Christoph von der Malsburg,et al.  The Correlation Theory of Brain Function , 1994 .

[15]  R. Traub,et al.  Spread of synchronous firing in longitudinal slices from the CA3 region of the hippocampus. , 1988, Journal of neurophysiology.

[16]  G Tononi,et al.  Modeling perceptual grouping and figure-ground segregation by means of active reentrant connections. , 1991, Proceedings of the National Academy of Sciences of the United States of America.

[17]  B. Julesz.  Dialogues on Perception , 1994 .

[18]  DeLiang Wang,et al.  Emergent synchrony in locally coupled neural oscillators , 1995, IEEE Trans. Neural Networks.

[19]  S. Grossberg.  Neural Networks and Natural Intelligence , 1988 .

[20]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[21]  Ke Chen,et al.  A self-generating modular neural network architecture for supervised learning , 1997, Neurocomputing.

[22]  Jack D. Cowan,et al.  Traveling activity waves , 1998 .

[23]  K. Lang,et al.  Learning to tell two spirals apart , 1988 .

[24]  DeLiang Wang,et al.  Image Segmentation Based on Oscillatory Correlation , 1997, Neural Computation.

[25]  Deliang Wang,et al.  Global competition and local cooperation in a network of neural oscillators , 1995 .

[26]  S. Palmer,et al.  Rethinking perceptual organization: The role of uniform connectedness , 1994, Psychonomic bulletin & review.

[27]  C. Gilbert.  Horizontal integration and cortical dynamics , 1992, Neuron.