Tohru Nitta

Tohru Nitta received a BS degree in mathematics, MS and PhD degrees in information science from University of Tsukuba (Japan) in 1983, 1985, and 1995 respectively. From 1985 to 1990, he was with NEC Corporation and engaged in research on expert systems. He joined the Electrotechnical Laboratory, Agency of Industrial Science and Technology, Ministry of International Trade and Industry (1990). He is currently a senior research Scientist in National Institute of Advanced Industrial Science and Technology (former Electrotechnical Laboratory), Japan. He was also with Department of Mathematics, Graduate School of Science, Osaka University as an associate professor from 2000 to 2006, and as a professor from 2006 to 2008 (additional post). His research interests include complex adaptive systems such as neural networks.

Publications

Widely Linear Estimation with Geometric Algebra
Widely Linear Estimation with Geometric Algebra
Tohru Nitta. © 2013. 16 pages.
This chapter reviews the widely linear estimation for complex numbers, quaternions, and geometric algebras (or Clifford algebras) and their application examples. It was proved...
Learning Transformations with Complex-Valued Neurocomputing
Learning Transformations with Complex-Valued Neurocomputing
Tohru Nitta. © 2012. 36 pages.
The ability of the 1-n-1 complex-valued neural network to learn 2D affine transformations has been applied to the estimation of optical flows and the generation of fractal...
Ability of the 1-n-1 Complex-Valued Neural Network to Learn Transformations
Ability of the 1-n-1 Complex-Valued Neural Network to Learn Transformations
Tohru Nitta. © 2011. 31 pages.
The ability of the 1-n-1 complex-valued neural network to learn 2D affine transformations has been applied to the estimation of optical flows and the generation of fractal...
Complex-Valued Neural Networks: Utilizing High-Dimensional Parameters
Complex-Valued Neural Networks: Utilizing High-Dimensional Parameters
Tohru Nitta. © 2009. 504 pages.
Recent research indicates that complex-valued neural networks whose parameters (weights and threshold values) are all complex numbers are in fact useful, containing...
Complex-Valued Neural Networks
Complex-Valued Neural Networks
Tohru Nitta. © 2009. 6 pages.
The usual real-valued artificial neural networks have been applied to various fields such as telecommunications, robotics, bioinformatics, image processing and speech...