N
Nobuyuki Matsui
Researcher at University of Hyogo
Publications - 196
Citations - 2148
Nobuyuki Matsui is an academic researcher from University of Hyogo. The author has contributed to research in topics: Artificial neural network & Cellular automaton. The author has an hindex of 23, co-authored 195 publications receiving 1980 citations. Previous affiliations of Nobuyuki Matsui include Hyogo University & Artificial Intelligence Center.
Papers
More filters
Book ChapterDOI
On a Universal Brownian Cellular Automata with 3 States and 2 Rules
TL;DR: A 3-state asynchronous CA that requires merely two transition rules to achieve computational universality is presented, achieved by embedding Priese’s delay-insensitive circuit elements on the cell space of a so-called Brownian CA.
Proceedings ArticleDOI
On Determination of Ophthalmic Examinations Using Support Vector Machines
TL;DR: The proposed method of determining examination groups is presented for new outpatients visiting the department of ophthalmology, using support vector machines (SVM's) and achieves as favorable accuracy as the first determination made by an average ophthalmologist.
Proceedings ArticleDOI
On defect-tolerance in cellular computers
TL;DR: A self-contained way to detect defects in a cellular array, and to configure circuits on its cells while avoiding the defects is shown.
Proceedings ArticleDOI
Synchronization and stochasticity of neural activity in perceptual alternation of ambiguous figures
TL;DR: A dynamical neural network model is presented to show critical roles of neural synchronization and stochastic noise in perceptual alternation of ambiguous figures, and it is shown that stoChastic fluctuation added to neural activity plays an essential role in obtaining perceptualAlternation.
Proceedings ArticleDOI
Learning-based on-line testing in feedforward neural networks
TL;DR: Learning-based on-line testing in feedforward neural networks (NNs) is discussed, and the re-learning employing two sigmoid activation functions per neuron in the last layer of the NN is made to set up the range of erroneous potentials produced from the last layers.