Bifurcations in the learning of recurrent neural networks

2003/01/02 by Kenji Doya · 3 citations
Computer Science · Physics and Astronomy · #Neural Networks and Applications #Neural Networks and Reservoir Computing #Model Reduction and Neural Networks

paper · doi:10.1109/iscas.1992.230622

openalex publication_date 2003/01/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/29

Abstract

Gradient descent algorithms in recurrent neural networks can have problems when the network dynamics experience bifurcations in the course of learning. The possible hazards caused by the bifurcations of the network dynamics and the learning equations are investigated. The roles of teacher forcing, preprogramming of network structures, and the approximate learning algorithms are discussed.>

Citations

• Finding Structure in Time

Cited by

• Robust timing and motor patterns by taming chaos in recurrent neural networks
• Pop Music Transformer: Beat-based Modeling and Generation of Expressive Pop Piano Compositions
• Vanishing gradient problem [wikipedia]