Analog versus Discrete Neural Networks

  • Bhaskar DasGupta Georg SchnitgerDepartment
  • Published 1996

Abstract

We show that neural networks with three-times continuously diierentiable activation functions are capable of computing a certain family of n-bit Boolean functions with two gates, whereas networks composed of binary threshold functions require at least (log n) gates. Thus, for a large class of activation functions, analog neural networks can be more powerful… (More)

Topics

  • Presentations referencing similar topics