Pattern processing and stability criteria in cellular logic networks
β Scribed by M.C. Fairhurst; G.P. Goutos
- Publisher
- Elsevier Science
- Year
- 1980
- Weight
- 316 KB
- Volume
- 12
- Category
- Article
- ISSN
- 0020-7373
No coin nor oath required. For personal study only.
β¦ Synopsis
An important factor in the application of dynamic cellular logic networks to pattern processing tasks is the stability of the network, defined in terms of the number of modes of activity which it can exhibit. This paper presents results which resolve a potential conflict in choosing the number of inputs per network element between increasing the network stability and reducing its capacity for discrimination. Implications for pattern processing in practical pattern classifiers and in neural networks are discussed.
π SIMILAR VOLUMES
The use of "control parameters" as applied to describe the dynamics of complex mathematical systems within models of real social systems is discussed. Whereas single control parameters cannot sufficiently characterize the dynamics of such systems it is suggested that domains of values of certain set