Multiple descent cost competitive learning: Batch and successive self-organization with excitatory and inhibitory connections

Novel general algorithms for multiple-descent cost-competitive learning are presented. These algorithms self-organize neural networks and possess the following features: optimal grouping of applied vector inputs, product form of neurons, neural topologies, excitatory and inhibitory connections, fair competitive bias, oblivion, winner-take-quota rule, stochastic update, and applicability to a wide class of costs. Both batch and successive training algorithms are given. Each type has its own merits. However, these two classes are equivalent, since a problem solved in the batch mode can be computed successively, and vice versa. The algorithms cover a class of combinatorial optimizations besides traditional standard pattern set design.