Self-consistent signal-to-noise analysis and its application to analogue neural networks with asymmetric connections
Masatoshi Shiino, Tomoki Fukai · Journal of Physics A Mathematical and General · 1992
A new systematic method is proposed for the analysis of the storage capacity of analogue neural networks with general input-output relations. It is based on the self-consistent signal-to-noise analysis in which renormalization of the signal part in the local field is properly performed. A remarkable feature of the present recipe, which in the case of symmetric analogue networks yields the same result as obtained by replica calculations, is the capability of dealing with asymmetric networks of analogue neurons. The theory is applied for the asymmetric network in which each neuron is loaded with biased patterns while some neurons are assigned only to extend inhibitory synaptic couplings free of learning.