Learning of Periodic Attractors in Simple Dynamic Binary Neural Networks
Conference: NDES 2012 - Nonlinear Dynamics of Electronic Systems
07/11/2012 - 07/13/2012 at Wolfenbüttel, Germany
Proceedings: NDES 2012
Pages: 4Language: englishTyp: PDFPersonal VDE Members are entitled to a 10% discount on this title
Kouzuki, Ryota; Suzuki, Takayoshi; Saito, Toshimichi (EE Department, HOSEI University)
This paper studies learning capability of simple dynamic binary neural networks characterized by signum activation function and ternary weighting parameters. Applying a correlation-based learning method, the network can store a class of periodic attractors. The network dynamics can be integrated into a simple return map on lattice points and we can grasp basic characteristics such as the number of periodic attractors and their domain of attraction. Performing basic numerical experiments, typical network dynamics learning examples are demonstrated.