Neural Nets and Implicit Inference
Whittle, P.
Ann. Appl. Probab., Tome 1 (1991) no. 4, p. 173-188 / Harvested from Project Euclid
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.
Publié le : 1991-05-14
Classification:  Neural nets,  association,  memory,  Hopfield net,  antiphon,  channel coding,  62H15,  93A15,  94A24
@article{1177005932,
     author = {Whittle, P.},
     title = {Neural Nets and Implicit Inference},
     journal = {Ann. Appl. Probab.},
     volume = {1},
     number = {4},
     year = {1991},
     pages = { 173-188},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1177005932}
}
Whittle, P. Neural Nets and Implicit Inference. Ann. Appl. Probab., Tome 1 (1991) no. 4, pp.  173-188. http://gdmltest.u-ga.fr/item/1177005932/