Genetic Generation of Both the Weights and Architecture for a Neural Network

@inproceedings{Koza1991GeneticGO,
  title={Genetic Generation of Both the Weights and Architecture for a Neural Network},
  author={John R. Koza and James P. Rice},
  year={1991}
}
This paper shows how to find both the weights and architecture for a neural network (including the number of layers, the number of processing elements per layer, and the connectivity between processing elements). This is accomplished using a recently developed extension to the genetic algorithm which genetically breeds a population of LISP symbolic expressions (S-expressions) of varying size and shape until the desired performance by the network is successfully evolved. The new "genetic… CONTINUE READING
Highly Influential
This paper has highly influenced a number of papers. REVIEW HIGHLY INFLUENTIAL CITATIONS