An Accelerating Learning Algorithm for Block-Diagonal Recurrent Neural Networks

An efficient training method for block-diagonal recurrent neural networks is proposed. The method modifies the RPROP algorithm, originally developed for static models, in order to be applied to dynamic systems. A comparative analysis with a series of algorithms and recurrent models is given, indicating the effectiveness of the proposed learning approach.

• Type: Conference
• Year: 2005
• Where: CIMCA
• Authors: Paris A. Mastorocostas, Dimitris N. Varsamis, Constantinos A. Mastorocostas, Ioannis Rekanos
• Keywords: CIMCA 2005, Efficient Training Method, Recurrent Models, Recurrent Neural Networks