Japanese

Masaharu Adachi

Name Masaharu Adachi
Position Professor
Degree(s) Ph.D.
Main Subjects Fundamentals of Electrical Circuit
Electric Circuit Theory and Practice I
System Engineering
Engineering English
Workshop
Masaharu Adachi
Specialty Nonlinear system engineering
Field of Research Supervised and unsupervised learning for artificial neural networks.
Associative memory especially with chaotic dynamics.
Nonlinear time series prediction.
Academic Society IEEE
Short Curriculum Vitae Mar. 1989 : B.E. degree in electronic engineering from Tokyo Denki University
Mar. 1994 : Ph.D. from Tokyo Denki University
Apr. 1994 : Research Officer of The University of Western Australia
May. 1995 : Postdoctral Researcher of RIKEN Institute
Oct. 1998 : Assistant Professor
Oct. 2000 : Associate Professor
Oct. 2006 : Professor
Mail

Selected Papers

  • Yusuke Tabata and Masaharu Adachi: A Spiking Network of Hippocampal Model Including Neurogenesis, Lecture Notes in Computer Science, vol. 5506/2009, pp.14–21, 2009.
  • Norihisa Sato and Masaharu Adachi: Synchronization of Chaotic Systems without Direct Connections Using Reinforcement Learning, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol.E92-A, no.4, pp.958–965, 2009.
  • Masaharu Adachi and Kazuyuki Aihara: An Analysis on Instantaneous Stability of an Associative Chaotic Neural Network, International Journal of Bifurcations and Chaos, vol. 9, no. 11, pp. 2157–2163, 1999.
  • Masaharu Adachi and Kazuyuki Aihara: Associative Dynamics in A Chaotic Neural Network, INNS Neural Networks, vol. 10, no. 1, pp. 83–98, 1997.
  • Masaharu Adachi and Makoto Kotani: Identification of Chaotic Dynamical Systems with Back-Propagation Neural Networks, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol. E77-A, pp. 324–334, 1994.

Laboratory Introduction

The laboratory members work for the following projects.

  • Improveing learning rules both of supervised and unspervised learning.
  • Associative memory especially with chaotic dynamics.
  • Application of artificial neural networks especially on time series prediction and analysis of functional near-infrared spectroscopy data.

Learning Systems Laboratory

Back to Top