Optimal storage capacity of neural networks at finite temperatures

dc.creatorShimi, G. M.
dc.creatorKim, D.
dc.creatorChoi, M. Y.
dc.date1993-06-15
dc.date.accessioned2026-07-07T03:06:52Z
dc.date.available2026-07-07T03:06:52Z
dc.descriptionGardner's analysis of the optimal storage capacity of neural networks is extended to study finite-temperature effects. The typical volume of the space of interactions is calculated for strongly-diluted networks as a function of the storage ratio $α$, temperature $T$, and the tolerance parameter $m$, from which the optimal storage capacity $α_c$ is obtained as a function of $T$ and $m$. At zero temperature it is found that $α_c = 2$ regardless of $m$ while $α_c$ in general increases with the tolerance at finite temperatures. We show how the best performance for given $α$ and $T$ is obtained, which reveals a first-order transition from high-quality performance to low-quality one at low temperatures. An approximate criterion for recalling, which is valid near $m=1$, is also discussed.
dc.description22 pages in LaTex, 4 figures upon request, SNUTP-93-26
dc.identifierhttps://arxiv.org/abs/cond-mat/9306032
dc.identifierhttp://arxiv.org/abs/cond-mat/9306032
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/26970
dc.subjectCondensed Matter
dc.titleOptimal storage capacity of neural networks at finite temperatures
dc.typetext

Files

Collections