Amit, Daniel J.; Campbell, C.; Wong, K. Y. M. The interaction space of neural networks with sign-constrained synapses. (English) Zbl 0727.68091 J. Phys. A, Math. Gen. 22, No. 21, 4687-4693 (1989). We investigate the optimal storage capacity of attractor neural networks with sign-constrained weights, which are prescribed a priori. The storage capacity is calculated by considering the fractional volume of weights which can store a set of random patterns as attractors, for a given stability parameter. It is found that this volume is independent of the particular distribution of signs (gauge invariance) and that the storage capacity of such constrained networks is exactly one half that of the unconstrained network with the corresponding value of the stability parameter. Cited in 4 Documents MSC: 68T05 Learning and adaptive systems in artificial intelligence 68P20 Information storage and retrieval of data Keywords:learning algorithm; storage capacity; attractor neural networks PDFBibTeX XMLCite \textit{D. J. Amit} et al., J. Phys. A, Math. Gen. 22, No. 21, 4687--4693 (1989; Zbl 0727.68091) Full Text: DOI