Classification and Lumpability in the Stochastic Hopfield Model
Abstract
Connections between classification and lumpability in the stochastic Hopfield model (SHM) are explored and developed. A simplification of the SHM's complexity based upon its inherent lumpability is derived. Contributions resulting from this reduction in complexity include: (i) computationally feasible classification time computations (ii) a development of techniques for enumerating the stationary distribution of the SHM's energy function and (iii) a characterization of the set of possible absorbing states of the Markov chain associated with the zero temperature SHM.
Recommended Citation
R. Paige, "Classification and Lumpability in the Stochastic Hopfield Model," Advances in Applied Probability, Applied Probability Trust, Jan 2001.
The definitive version is available at https://doi.org/10.1239/aap/1011994037
Department(s)
Mathematics and Statistics
Keywords and Phrases
Classification times; neural networks
International Standard Serial Number (ISSN)
0001-8678
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2001 Applied Probability Trust, All rights reserved.
Publication Date
01 Jan 2001
