Y
Yoshitsugu Kakemoto
Researcher at JSOL
Publications - 4
Citations - 1
Yoshitsugu Kakemoto is an academic researcher from JSOL. The author has contributed to research in topics: Hybrid neural network & Artificial neural network. The author has an hindex of 1, co-authored 4 publications receiving 1 citations.
Papers
More filters
Proceedings ArticleDOI
Vibrate Synchronize Function neural network model — Its backgrounds
TL;DR: In this paper, the two theoretical backgrounds of VSF-Network are introduced and an incremental learning framework with Chaos Neural Networks and the pattern recognition with the combined with symbols is introduced by Stochastic Catastrophe Model.
Proceedings ArticleDOI
Selective connection weight update, its background and experimental considerations
TL;DR: It is shown that VSF-network can recognize combined patterns only if it has learned parts of the patterns and factors for affecting performance of the learning are shown.
Proceedings ArticleDOI
Analysis of inner structure of VSF-Network
TL;DR: A theoretical analysis on the internal structure and learning method of VSF-Network, a hybrid neural network combining hierarchical neural network and the chaotic neural network, which explains from the viewpoint of the combination of the divided linear spaces that the subnetworks obtained by learning can be recognized in combination according to the situation.
Book ChapterDOI
Selective weight update rule for hybrid neural network
TL;DR: The two theoretical backgrounds of VSF---Network are described and it is shown that VSF-network can recognize combined patterns only if it has learned parts of the patterns and factors for affecting performance of the learning.