Evolutionary Induction of Sparse Neural

  • TreesByoung-Tak Zhang, Peter Ohm, Heinz M uhlenbeinDept
  • Published 1997

Abstract

This paper is concerned with the automatic induction of parsimonious neural networks. In contrast to other program induction situations, network induction entails parametric learning as well as structural adaptation. We present a novel representation scheme, called neural trees, that allows eecient learning of network architectures and parameters both by… (More)

Topics

  • Presentations referencing similar topics