R Smalz | PubMed Health

PubMed1995

Evolutionary credit apportionment and its application to time-dependent neural processing.

A new approach to training recurrent neural networks is applied to temporal neural processing problems. Our method combines Darwinian variation and selection with a credit apportionment mechanism for assigning credit to individual neurons within the groups of competing networks. Interconnections between the networks allow the outputs of neurons in one network to be available to the neurons in other networks. The firing behavior of the neurons in a variety of networks is compared with the corresponding neurons in high performing networks for specific input contexts. Payoffs accorded to neurons in one network can thus be shared with neurons in other networks. Only the best neurons over the entire repertoire of networks are allowed to pass their crucial function-determining parameters on to other neurons. The algorithm is demonstrated with connectionist-type units on several temporal processing tasks and compared to genetic algorithms.

Algorithms↗

PubMed1989

Towards an artificial brain.

Three components of a brain model operating on neuromolecular computing principles are described. The first component comprises neurons whose input-output behavior is controlled by significant internal dynamics. Models of discrete enzymatic neurons, reaction-diffusion neurons operating on the basis of the cyclic nucleotide cascade, and neurons controlled by cytoskeletal dynamics are described. The second component of the model is an evolutionary learning algorithm which is used to mold the behavior of enzyme-driven neurons or small networks of these neurons for specific function, usually pattern recognition or target seeking tasks. The evolutionary learning algorithm may be interpreted either as representing the mechanism of variation and natural selection acting on a phylogenetic time scale, or as a conceivable ontogenetic adaptation mechanism. The third component of the model is a memory manipulation scheme, called the reference neuron scheme. In principle it is capable of orchestrating a repertoire of enzyme-driven neurons for coherent function. The existing implementations, however, utilize simple neurons without internal dynamics. Spatial navigation and simple game playing (using tic-tac-toe) provide the task environments that have been used to study the properties of the reference neuron model. A memory-based evolutionary learning algorithm has been developed that can assign credit to the individual neurons in a network. It has been run on standard benchmark tasks, and appears to be quite effective both for conventional neural nets and for networks of discrete enzymatic neurons. The models have the character of artificial worlds in that they map the hierarchy of processes in the brain (at the molecular, neuronal, and network levels), provide a task environment, and use this relatively self-contained setup to develop and evaluate learning and adaptation algorithms.

Artificial Intelligence↗