Learning long-term motor timing/patterns on an orthogonal basis in random neural networks.

Autor: Kawai Y; Symbiotic Intelligent Systems Research Center, Institute for Open and Transdisciplinary Research Initiatives, Osaka University, 1-1 Yamadaoka, Suita, Osaka 565-0871, Japan. Electronic address: kawai@otri.osaka-u.ac.jp., Park J; Symbiotic Intelligent Systems Research Center, Institute for Open and Transdisciplinary Research Initiatives, Osaka University, 1-1 Yamadaoka, Suita, Osaka 565-0871, Japan; Center for Information and Neural Networks, National Institute of Information and Communications Technology, 1-4 Yamadaoka, Suita, Osaka 565-0871, Japan., Tsuda I; Chubu University Academy of Emerging Sciences/Center for Mathematical Science and Artificial Intelligence, Chubu University, 1200 Matsumoto-cho, Kasugai, Aichi 487-8501, Japan., Asada M; Symbiotic Intelligent Systems Research Center, Institute for Open and Transdisciplinary Research Initiatives, Osaka University, 1-1 Yamadaoka, Suita, Osaka 565-0871, Japan; Center for Information and Neural Networks, National Institute of Information and Communications Technology, 1-4 Yamadaoka, Suita, Osaka 565-0871, Japan; Chubu University Academy of Emerging Sciences/Center for Mathematical Science and Artificial Intelligence, Chubu University, 1200 Matsumoto-cho, Kasugai, Aichi 487-8501, Japan; International Professional University of Technology in Osaka, 3-3-1 Umeda, Kita-ku, Osaka 530-0001, Japan.
Jazyk: angličtina
Zdroj: Neural networks : the official journal of the International Neural Network Society [Neural Netw] 2023 Jun; Vol. 163, pp. 298-311. Date of Electronic Publication: 2023 Apr 12.
DOI: 10.1016/j.neunet.2023.04.006
Abstrakt: The ability of the brain to generate complex spatiotemporal patterns with specific timings is essential for motor learning and temporal processing. An approach that can model this function, using the spontaneous activity of a random neural network (RNN), is associated with orbital instability. We propose a simple system that learns an arbitrary time series as the linear sum of stable trajectories produced by several small network modules. New finding in computer experiments is that the trajectories of the module outputs are orthogonal to each other. They created a dynamic orthogonal basis acquiring a high representational capacity, which enabled the system to learn the timing of extremely long intervals, such as tens of seconds for a millisecond computation unit, and also the complex time series of Lorenz attractors. This self-sustained system satisfies the stability and orthogonality requirements and thus provides a new neurocomputing framework and perspective for the neural mechanisms of motor learning.
Competing Interests: Declaration of Competing Interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Yuji Kawai reports financial support was provided by Japan Science and Technology Agency. Minoru Asada reports financial support was provided by New Energy and Industrial Technology Development Organization.
(Copyright © 2023 The Author(s). Published by Elsevier Ltd.. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: