✦ LIBER ✦

On the Storage Capacity of Nonlinear Neural Networks

✍ Scribed by Christian Mazza

Publisher: Elsevier Science
Year: 1997
Tongue: English
Weight: 1000 KB
Volume: 10
Category: Article
ISSN: 0893-6080
DOI: 10.1016/s0893-6080(97)00017-8

No coin nor oath required. For personal study only.

✦ Synopsis

We consider the Hopfield associative memory for storing m patterns xi(r) in { - 1, + 1}(n), r = 1, em leader,m. The weights are given by the scalar product model w(ij)=(m/n)G,i not equal j,w(ii) identical with 0, where G:R --> R is some nonlinear function, like G(x) z.tbnd6; Sgn(x), which is used in hardware implementation of associative memories. We give a rigorous lower bound for the memory size of this (ANN) by using large deviations estimates. Our main results states that retrieval without errors occurs when m(n) --> infinity as n --> infinity in such a way that m(n) < (n/2log(n))q(G), where 0 < q(G): = E(NG)N))(2)/E(G(N)(2)))

📜 SIMILAR VOLUMES

The storage capacity of the complex phas

The storage capacity of the complex phasor neural network

✍ Zhenxiang Chen; Jianwei Shuai; Jincheng Zheng; Riutang Liu; Boxi Wu 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 321 KB

In this paper, the storage capacity of the Q-state complex phasor neural network is analysed with the signal-to-noise theory. The results indicate that the storage capacity of the model approaches that of the Hopfield model if the number Q is small; while the storage capacity is proportional to Q-2

Optimal storage capacity for diluted mul

Optimal storage capacity for diluted multi-state neural networks: continuous and discrete couplings

✍ D. Bollé; P. Dupont; J. van Mourik 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 212 KB

Information capacity of outer-product ne

Information capacity of outer-product neural networks

✍ James D. Keeler 📂 Article 📅 1987 🏛 Elsevier Science 🌐 English ⚖ 411 KB

Applications of information storage matr

Applications of information storage matrix neural networks

✍ Nikola Samardzija 📂 Article 📅 1993 🏛 Elsevier Science 🌐 English ⚖ 819 KB

The stability and design of nonlinear ne

The stability and design of nonlinear neural networks

✍ Xiangyang Gong; Wanyi Chen; Fengsheng Tu 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 363 KB

Based on the techniques of singular value decomposition and generalized inverse, two new methods for designing associative memories are presented. The two methods not only guarantee that each given vector is an equilibrium point of the network, but also guarantee the asymptotic stability of the equi

Storage of words in a neural network

✍ Patricio Perez; Giovanni Salini 📂 Article 📅 1993 🏛 Elsevier Science 🌐 English ⚖ 441 KB