Pattern categorization and generalization with a virtual neuromolecular architecture

A multilevel neuromolecular computing architecture has been developed that provides a rich platform for evolutionary learning. The architecture comprises a network of neuron-like modules with internal dynamics modeled by cellular automata. The dynamics are motivated by the hypothesis that molecular processes operative in real neurons (in particular processes connected with second messenger signals and cytoskeleton-membrane inter actions) subserve a signal integrating function. The objective is to create a repertoire of special purpose dynamic pattern processors through an evolutionary search algorithm and then to use memory manipulation algorithms to select combinations of processors from the repertoire that are capable of performing coherent pattern recognition/neurocontrol tasks. The system consists of two layers of cytoskeletally controlled (enzymatic) neurons and two layers of memory access neurons (called reference neurons) divined into a collection of functionally comparable subnets. Evolutionary learning can occur at the intraneuronal level through variations in the cytoskeletal structures responsible for the integration of signals in space and time, through variations in the location of elements that represent readin or readout proteins, and through variations in the connectivity of the neurons. The memory manipulation algorithms that orchestrate the repertoire of neuronal processors also use evolutionary search procedures. The network is capable of performing complicated pattern categorization tasks and of doing so in a manner that balances specificity and generalization. Copyright (C) 1996 Elsevier Science Ltd.