NeuroCOLT

Neural Networks and Computational Learning Theory

About NeuroCOLT

Papers Archive

Books

info@neurocolt.org

NeuroCOLT Technical Report NC-TR-95-051

On the Computational Power of Continuous Time Neural Networks

Pekka Orponen
University of Helsinki
Finland

Abstract
We investigate the computational power of continuous-time neural networks with Hopfield-type units. We prove that polynomial-size networks with saturated-linear response functions are at least as powerful as polynomially space-bounded Turing machines.

Download Compressed Postscript