Generation, local receptive fields and global convergence improve perceptual learning in connectionist networks

Authors:
Vasant Honavar;Leonard Uhr
Affiliations:
Computer Sciences Department, University of Wisconsin-Madison;Computer Sciences Department, University of Wisconsin-Madison
Venue:
IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Year:
1989

Citing 6
Cited 0

Learning translation invariant recognition in massively parallel networks

Volume I: Parallel architectures on PARLE: Parallel Architectures and Languages Europe
Pyramid vision using key features to integrate image-driven bottom-up and model-driven top-down processes

IEEE Transactions on Systems, Man and Cybernetics - Special issue on artificial intelligence
Certain aspects of the anatomy and physiology of the cerebral cortex

Parallel distributed processing: explorations in the microstructure of cognition, vol. 2
Highly parallel, hierarchical, recognition cone perceptual structures

Parallel computer vision
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Layered "Recognition Cone" Networks That Preprocess, Classify, and Describe

IEEE Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents and compares results for three types of connectionist networks on perceptual learning tasks: [A] Multi-layered converging networks of neuron-like units, with each unit connected to a small randomly chosen subset of units in the adjacent layers, that learn by re-weighting of their links; [B] Networks of neuron-like units structured into successively larger modules under brain-like topological constraints (such as layered, converging-diverging hierarchies and local receptive fields) that learn by re-weighting of their links; [C] Networks with brain-like structures that learn by generation-discovery, which involves the growth of links and recruiting of units in addition to reweighting of links. Preliminary empirical results from simulation of these networks for perceptual recognition tasks show significant improvements in learning from using brain-like structures (e.g., local receptive fields, global convergence) over networks that lack such structure; further improvements in learning result from the use of generation in addition to reweighting of links.