Abstract
The contention that artificial neural nets operate by a process of distributed hypothesis testing is supported by analysis of the antiphon, a model which is close to standard associative-memory models but is intended primarily to represent memory storage under stochastic disturbance of the system. The memory capacity of the antiphon under "neuronal" inference rules has been evaluated elsewhere; here it is evaluated under the supposition of efficient inference procedures.
Citation
P. Whittle. "Neural Nets and Implicit Inference." Ann. Appl. Probab. 1 (2) 173 - 188, May, 1991. https://doi.org/10.1214/aoap/1177005932
Information
