K
Kazuyuki Hara
Researcher at College of Industrial Technology
Publications - 53
Citations - 567
Kazuyuki Hara is an academic researcher from College of Industrial Technology. The author has contributed to research in topics: Ensemble learning & Perceptron. The author has an hindex of 9, co-authored 52 publications receiving 423 citations. Previous affiliations of Kazuyuki Hara include Kanazawa University & Nihon University.
Papers
More filters
Proceedings ArticleDOI
Analysis of function of rectified linear unit used in deep learning
TL;DR: A rectified linear unit (ReLU) is proposed to speed up the learning convergence of the deep learning using a using simpler network called the soft-committee machine and the reasons for the speedup are clarified.
Book ChapterDOI
Analysis of Dropout Learning Regarded as Ensemble Learning
TL;DR: It is found that the process of combining the neglected hidden units with the learned network can be regarded as ensemble learning, so dropout learning is analyzed from this point of view.
Journal ArticleDOI
Analysis of ensemble learning using simple perceptrons based on online learning theory.
TL;DR: This paper shows that ensemble generalization error can be calculated by using two order parameters, that is, the similarity between a teacher and a student, and the similarity among students.
Proceedings ArticleDOI
Comparison of activation functions in multilayer neural network for pattern classification
Kazuyuki Hara,K. Nakayamma +1 more
TL;DR: Property of activation functions in multilayer neural network applied to pattern classification is discussed, and a rule of thumb for selecting activation functions or their combination is proposed.
Journal ArticleDOI
Ensemble Learning of Linear Perceptrons: On-Line Learning Theory
TL;DR: In this article, linear perceptrons are used as teacher and student for ensemble learning, including the noisy case where teacher or student noise is present, and the homogeneous correlation of the correlation is analyzed.