Establishing Innovative Machine Learning Mechanism by Cerebellar Spiking Neural Networks

2017 Fiscal Year Final Research Report

• Project/Area Number: 15K21471
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Soft computing; Intelligent informatics
• Research Institution: Chiba Institute of Technology (2017); Fukui University of Technology (2015-2016)
• Principal Investigator: Nobukawa Sou 千葉工業大学, 情報科学部, 准教授 (70724558)
• Research Collaborator: Nishimura Haruhiko 兵庫県立大学, 大学院・応用情報科学研究科, 教授 ; Yamanishi Teruya 福井工業大学, 環境情報科学部・経営情報学科, 教授
• Project Period (FY): 2015-04-01 – 2018-03-31
• Keywords: スパイキングニューラルネットワーク / カオス / カオス共鳴 / 小脳 / 下オリーブ核

Outline of Final Research Achievements

It is well known that conventional machine learning methods cannot be adopted against dynamically changing systems, adequately. Wile, we have attempted to establish innovative machine learning mechanism, which can be adopted to such systems, by cerebellar spiking neural networks. As the results, we have constructed the spiking neuron models and their networks corresponding to physiological cerebellar learning system. This cerebellar spiking neural network induces the chaotic resonance that enhances the learning ability.

Free Research Field

計算論的神経科学