H
Haruhiko Nishimura
Researcher at University of Hyogo
Publications - 198
Citations - 2312
Haruhiko Nishimura is an academic researcher from University of Hyogo. The author has contributed to research in topics: Artificial neural network & Biological neuron model. The author has an hindex of 24, co-authored 196 publications receiving 2017 citations. Previous affiliations of Haruhiko Nishimura include Hyogo University of Teacher Education & Kobe University.
Papers
More filters
Journal Article
Quaternion neural network with geometrical operators
TL;DR: This paper shows by experiments that the quaternion-version of the Back Propagation algorithm achieves correct geometrical transformations in three-dimensional space, as well as in color space for an image compression problem, whereas real-valued BP algorithms fail.
Journal ArticleDOI
Qubit neural network and its learning efficiency
TL;DR: Simulations have shown that the Qubit model solves learning problems with significantly improved efficiency as compared to the classical model, and it is suggested that the improved performance is due to the use of superposition of neural states and theUse of probability interpretation in the observation of the output states of the model.
Journal ArticleDOI
Associative memory in quaternionic Hopfield neural network.
TL;DR: Associative memory networks based on quaternionic Hopfield neural network are investigated and it is clarified that there exist at most 16 stable states, called multiplet components, as the degenerated stored patterns, and each of these states has its basin in the quaternion networks.
Journal ArticleDOI
A network model based on qubitlike neuron corresponding to quantum circuit
TL;DR: In this paper, a qubit-like neural network is constructed for a 3-bit quantum circuit, which is the minimum quantum logical gate describing all basic logical operations, and in this model, how to determine circuit parameters by learning.
Journal ArticleDOI
Image Compression by Layered Quantum Neural Networks
TL;DR: The performance of the quantum neural network of large size in image compression problems is evaluated to estimate the utility for the practical applications comparing with the conventional network consists of formal neuron model.