Associative learning in hierarchical self organizing learning arrays

Authors:
Janusz A. Starzyk;Zhen Zhu;Yue Li
Affiliations:
School of Electrical Engineering and Computer Science, Ohio University, Athens, OH;School of Electrical Engineering and Computer Science, Ohio University, Athens, OH;School of Electrical Engineering and Computer Science, Ohio University, Athens, OH
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Year:
2005

Citing 7
Cited 0

Bidirectional associative memories

IEEE Transactions on Systems, Man and Cybernetics
Neurocomputing

Neurocomputing
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Sparsely connected, Hebbian networks with strikingly large storage capacities

Neural Networks
Auto-associative memory produced by disinhibition in a sparsely connected network

Neural Networks
Multi-associative neural networks and their applications tolearning and retrieving complex spatio-temporal sequences

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Self-organizing learning array

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we introduce feedback based associative learning in self-organized learning arrays (SOLAR). SOLAR structures are hierarchically organized and have the ability to classify patterns in a network of sparsely connected neurons. These neurons may define their own functions and select their interconnections locally, thus satisfying some of the requirements for biologically plausible intelligent structures. Feed-forward processing is used to make necessary correlations and learn the input patterns. Associations between neuron inputs are used to generate feedback signals. These feedback signals, when propagated to the associated inputs, can establish the expected input values. This can be used for hetero and auto associative learning and pattern recognition.