2011/01/23 by Jacques M. Bahi, Christophe Guyeux, Bahi, Jacques M. +3
Computer Science · Physics and Astronomy · #Artificial Intelligence (cs.AI) #Blind Source Separation Techniques #Cryptography and Security (cs.CR) #Dynamical Systems (math.DS) #FOS: Computer and information sciences #FOS: Mathematics #General Topology (math.GN) #Model Reduction and Neural Networks #Neural Networks and Applications
paper · pdf · doi:10.48550/arxiv.1101.4351
openalex publication_date 2011/01/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Chaotic neural networks have received a great deal of attention these last years. In this paper we establish a precise correspondence between the so-called chaotic iterations and a particular class of artificial neural networks: global recurrent multi-layer perceptrons. We show formally that it is possible to make these iterations behave chaotically, as defined by Devaney, and thus we obtain the first neural networks proven chaotic. Several neural networks with different architectures are trained to exhibit a chaotical behavior.