Comparing Biases for Minimal Network Construction with Back-Propagation

  title={Comparing Biases for Minimal Network Construction with Back-Propagation},
  author={Stephen Jose Hanson and Lorien Y. Pratt},
Rumelhart (1987). has proposed a method for choosing minimal or "simple" representations during learning in Back-propagation networks. This approach can be used to (a) dynamically select the number of hidden units. (b) construct a representation that is appropriate for the problem and (c) thus improve the generalization ability of Back-propagation networks. The method Rumelhart suggests involves adding penalty terms to the usual error function. In this paper we introduce Rumelhart·s minimal… CONTINUE READING