A multiscale dynamic routing circuit for forming size- and position-invariant object representations
- 1 March 1995
- journal article
- Published by Springer Nature in Journal of Computational Neuroscience
- Vol. 2 (1) , 45-62
- https://doi.org/10.1007/bf00962707
Abstract
We describe a neural model for forming size- and position-invariant representations of visual objects. The model is based on a previously proposed dynamic routing circuit that remaps selected portions of an input array into an object-centered reference frame. Here, we show how a multiscale representation may be incorporated at the input stage of the model, and we describe the control architecture and dynamics for a hierarchical, multistage routing circuit. Specific neurobiological substrates and mechanisms for the model are proposed, and a number of testable predictions are described.Keywords
This publication has 40 references indexed in Scilit:
- A Nonlinear Hebbian Network that Learns to Detect Disparity in Random-Dot StereogramsNeural Computation, 1996
- Multiple processing streams in occipitotemporal visual cortexNature, 1994
- Dynamics of the Hippocampal Ensemble Code for SpaceScience, 1993
- Configuration, in Serial Reconstruction, of Individual Axons Projecting from Area V2 to V4 in the Macaque MonkeyCerebral Cortex, 1992
- Learning Invariance from Transformation SequencesNeural Computation, 1991
- The Bounded Brain: Toward Quantitative NeuroanatomyJournal of Cognitive Neuroscience, 1990
- Spatial mapping in the primate sensory projection: Analytic structure and relevance to perceptionBiological Cybernetics, 1977
- The neural representation of visual spaceNature, 1977
- Neuronal models for cognitive processes: Networks for learning, perception and imaginationJournal of Theoretical Biology, 1977
- Cooperative Computation of Stereo DisparityScience, 1976