Logo image
Computational-complexity reduction for neural network algorithms
Journal article

Computational-complexity reduction for neural network algorithms

A Guez, M Kam and J.L Eilbert
IEEE transactions on systems, man, and cybernetics, v 19(2), pp 409-414
Mar 1989

Abstract

Computational modeling Computer networks Couplings Differential equations Dynamic range Nerve fibers Neural networks Neurons Nonlinear equations State-space methods
An important class of neural models is described as a set of coupled nonlinear differential equations with state variables corresponding to the axon hillock potential of neurons. Through a nonlinear transformation, these models can be converted to an equivalent system of differential equations whose state variables correspond to firing rates. The firing rate formulation has certain computational advantages over the potential formulation of the model. The computational and storage burdens per cycle in simulations are reduced, and the resulting equations become quasilinear in a large significant subset of the state space. Moreover, the dynamic range of the state space is bounded, alleviating the numerical stability problems in network simulation. These advantages are demonstrated through an example, using the authors' model for the so-called neural solution to the traveling salesman problem proposed by J.J. Hopfield and D.W. Tank (1985).< >

Metrics

7 Record Views
2 citations in Scopus

Details

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Web of Science research areas
Computer Science, Cybernetics
Engineering, Electrical & Electronic
Logo image