Turing Universality of Neural Nets (Revisited)

We show how to use recursive function theory to prove Turing universality of finite analog recurrent neural nets, with a piecewise linear sigmoid function as activation function. We emphasize the modular construction of nets within nets, a relevant issue from the software engineering point of view. Keywords. Neural computation, recursive function theory, modularity.

• Type: Conference
• Year: 1997
• Where: EUROCAST
• Authors: João Pedro Guerreiro Neto, Hava T. Siegelmann, José Félix Costa, Carmen Paz Suárez Araujo
• Keywords: EUROCAST 1997, Hardware, Linear Sigmoid Function, Recurrent Neural Nets, Recursive Function Theory