A linear approximation for training Recurrent Random Neural Networks

Halici U., Karaoz E.

13th International Symposium on Computer and Information Sciences (ISCIS 98), BELEK ANTALYA, Turkey, 26 - 28 October 1998, vol.53, pp.149-156 identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 53
  • City: BELEK ANTALYA
  • Country: Turkey
  • Page Numbers: pp.149-156
  • Middle East Technical University Affiliated: Yes

Abstract

In this paper, a linear approximation for Gelenbe's Learning Algorithm developed for training Recurrent Random Neural Networks (RRNN) is proposed. Gelenbe's learning algorithm uses gradient descent of a quadratic error function in which the main computational effort is for obtaining the inverse of an n-by-n matrix. In this paper, the inverse of this matrix is approximated with a linear term and the efficiency of the approximated algorithm is examined when RRNN is trained as autoassociative memory.