@brazovayeye

A Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks

, , and . Genetic Programming 1996: Proceedings of the First Annual Conference, page 81--89. Stanford University, CA, USA, MIT Press, (28--31 July 1996)

Abstract

This paper compares the efficiency of two encoding schemes for Artificial Neural Networks optimised by evolutionary algorithms. Direct Encoding encodes the weights for an a priori fixed neural network architecture. Cellular Encoding encodes both weights and the architecture of the neural network. In previous studies, Direct Encoding and Cellular Encoding have been used to create neural networks for balancing 1 and 2 poles attached to a cart on a fixed track. The poles are balanced...

Links and resources

Tags

community

  • @schaul
  • @brazovayeye
  • @idsia
@brazovayeye's tags highlighted