Title:
|
Discontinuities in recurrent neural networks
|
Author:
|
Gavaldà Mestre, Ricard; Siegelmann, Hava T
|
Other authors:
|
Universitat Politècnica de Catalunya. Departament de Ciències de la Computació |
Abstract:
|
This paper studies the computational power of various discontinuous
real computational models that are based on the classical analog
recurrent neural network (ARNN). This ARNN consists of finite number
of neurons; each neuron computes a polynomial net-function and a
sigmoid-like continuous activation-function.
The authors introduce |
Subject(s):
|
-Àrees temàtiques de la UPC::Informàtica::Informàtica teòrica -Analog recurrent neural network -ARNN -Arithmetic networks |
Rights:
|
|
Document type:
|
Article - Published version Report |
Share:
|
|