Optimal storage capacity of neural networks at finite temperatures
| dc.creator | Shimi, G. M. | |
| dc.creator | Kim, D. | |
| dc.creator | Choi, M. Y. | |
| dc.date | 1993-06-15 | |
| dc.date.accessioned | 2026-07-07T03:06:52Z | |
| dc.date.available | 2026-07-07T03:06:52Z | |
| dc.description | Gardner'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.description | 22 pages in LaTex, 4 figures upon request, SNUTP-93-26 | |
| dc.identifier | https://arxiv.org/abs/cond-mat/9306032 | |
| dc.identifier | http://arxiv.org/abs/cond-mat/9306032 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/26970 | |
| dc.subject | Condensed Matter | |
| dc.title | Optimal storage capacity of neural networks at finite temperatures | |
| dc.type | text |