General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results

0404255 - UIVT-O 20030112 RIV US eng J - Journal Article
Šíma, Jiří - Orponen, P.
General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results.
Neural Computation. Roč. 15, č. 12 (2003), s. 2727-2778. ISSN 0899-7667. E-ISSN 1530-888X
R&D Projects: GA AV ČR IAB2030007; GA ČR GA201/02/1456
Institutional research plan: AV0Z1030915
Keywords : computational power * computational complexity * perceptrons * radial basis functions * spiking neurons * feedforward networks * reccurent networks * probabilistic computation * analog computation
Subject RIV: BA - General Mathematics
Impact factor: 2.747, year: 2003

We survey and summarize the literature on the computational aspects of neural network models by presenting a detailed taxonomy of the various models according to their complexity theoretic characteristics. The criteria of classification include the architecture of the network (feedforward versus recurrent), time model (discrete versus continuous), state type (binary versus analog), weight constraints (symmetric versus asymmetric), network size (finite nets versus infinite families), and computation type (deterministic vers probabilistic), among others. The underlying results concerning the computational power and complexity issues of perceptron, radial basis function, winner-take-all, and spiking neural networks are briefly surveyed, with pointers to the relevant literature. In our survey, we focus mainly on the digital computation whose inputs and outputs are binary in nature, although their values are quite often encoded as analog neuron states. We omit the important learning issu
Permanent Link: http://hdl.handle.net/11104/0124518