Attractor neural networks with global and local dilution of weights
Colin K. Campbell · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1992
We consider the generalization ability of dilute (partially connected) attractor neural networks. The generalization probability is considered for two types of dilution: networks in which the dilution is fixed before learning (local dilution) and networks in which the connectivity is decided during learning so as to optimize the storage capacity (global dilution).