Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Science / Faculty of Science >
Hokkaido University Preprint Series in Mathematics >
Singular-continuous nowhere-differentiable attractors in neural systems
Title: | Singular-continuous nowhere-differentiable attractors in neural systems |
Authors: | Tsuda, I. Browse this author | Yamaguchi, A. Browse this author |
Keywords: | Singular-continuous nowhere-differentiable attractors | Chaos-driven contraction dynamics | Information processings on Cantor set | Dimension gap |
Issue Date: | 1-Nov-1996 |
Publisher: | Department of Mathematics, Hokkaido University |
Journal Title: | Hokkaido University Preprint Series in Mathematics |
Volume: | 360 |
Start Page: | 1 |
End Page: | 24 |
Abstract: | We present a neural model for a singular-continuous nowhere-differentiable (SCND) attractors. This model shows various characteristics originated in attractor's nowheredifferentiability, in spite of a differentiable dynamical system. SCND attractors are still unfamiliar in the neural network studies and have not yet been observed in both artificial and biological neural systems. vVith numerical calculations of various kinds of statistical quantities in artificial neural network, dynamical characters of SCND attractors are strongly suggested to be observed also in neural systems experiments. vVe also present possible information processings with these attractors. |
Type: | bulletin (article) |
URI: | http://hdl.handle.net/2115/69110 |
Appears in Collections: | 理学院・理学研究院 (Graduate School of Science / Faculty of Science) > Hokkaido University Preprint Series in Mathematics
|
Submitter: 数学紀要登録作業用
|