M
Masaki Kobayashi
Researcher at University of Yamanashi
Publications - 141
Citations - 1327
Masaki Kobayashi is an academic researcher from University of Yamanashi. The author has contributed to research in topics: Artificial neural network & Content-addressable memory. The author has an hindex of 20, co-authored 139 publications receiving 1159 citations. Previous affiliations of Masaki Kobayashi include University of Tokyo & Okayama University.
Papers
More filters
Journal ArticleDOI
Hyperbolic Hopfield Neural Networks
TL;DR: The aim of this brief is to construct hyperbolic HNNs (HHNNs) as an analog of CHNNs, a typical complex-valued neuron model based on Lorentzian geometry.
Journal ArticleDOI
Electronic structure and magnetism of the diluted magnetic semiconductor Fe-doped ZnO nano-particles
T. Kataoka,Masaki Kobayashi,Y. Sakamoto,G. S. Song,Atsushi Fujimori,F.-H. Chang,Hong-Ji Lin,D. J. Huang,C. T. Chen,Takuo Ohkochi,Yukiharu Takeda,Tetsuo Okane,Yuichi Saitoh,Hiroshi Yamagami,Arata Tanaka,Sumantra Mandal,T. K. Nath,Debjani Karmakar,Indra Dasgupta +18 more
TL;DR: In this article, the electronic structure of Zn$0.9}$Fe$ 0.1}$O nano-particles was studied and it was shown that the room temperature ferromagnetism in the Zn $ 0.9]$Fe $ 0.1}O nanoparticles is primarily originated from the antiferromagnetic coupling between unequal amounts of Fe$^{3+}$ ions occupying two sets of nonequivalent positions in the region of the XMCD probing depth.
Journal ArticleDOI
Quaternionic Hopfield neural networks with twin-multistate activation function
TL;DR: A Hopfield neural network with a new quaternionic activation function, referred to as a twin-multistateactivation function, is proposed, which can take the place of the CHNNs with a multistate activation function.
Journal ArticleDOI
Twin-multistate commutative quaternion Hopfield neural networks
TL;DR: A commutative quaternion Hopfield neural network (CQHNN) is proposed as the analogy of QHNN, which is a multistate model of a Hopfeld neural network, and requires half the connection weight parameters of CHNN.
Journal ArticleDOI
Projection Rule for Rotor Hopfield Neural Networks
TL;DR: A projection rule is proposed for RHNN and it is demonstrated that the noise robustness of RHNN is better than that of CHNN, and the proposed algorithm improves the noise resilientness ofRHNN.