Projection learning algorithm for threshold - controlled neural networks

Journal Article · Wed Mar 01 04:00:00 EST 1995 · Cybernetics and Systems Analysis

OSTI ID:457600

Reznik, A M

The projection learning algorithm proposed in [1, 2] and further developed in [3] substantially improves the efficiency of memorizing information and accelerates the learning process in neural networks. This algorithm is compatible with the completely connected neural network architecture (the Hopfield network [4]), but its application to other networks involves a number of difficulties. The main difficulties include constraints on interconnection structure and the need to eliminate the state uncertainty of latent neurons if such are present in the network. Despite the encouraging preliminary results of [3], further extension of the applications of the projection algorithm therefore remains problematic. In this paper, which is a continuation of the work begun in [3], we consider threshold-controlled neural networks. Networks of this type are quite common. They represent the receptor neuron layers in some neurocomputer designs. A similar structure is observed in the lower divisions of biological sensory systems [5]. In multilayer projection neural networks with lateral interconnections, the neuron layers or parts of these layers may also have the structure of a threshold-controlled completely connected network. Here the thresholds are the potentials delivered through the projection connections from other parts of the network. The extension of the projection algorithm to the class of threshold-controlled networks may accordingly prove to be useful both for extending its technical applications and for better understanding of the operation of the nervous system in living organisms.

• OSTI ID: 457600
• Journal Information: Cybernetics and Systems Analysis, Journal Name: Cybernetics and Systems Analysis Journal Issue: 4 Vol. 30; ISSN CYASEC; ISSN 1060-0396
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
ALGORITHMS
ATTRACTORS
NEURAL NETWORKS