T
Takumi Ichimura
Researcher at Prefectural University of Hiroshima
Publications - 196
Citations - 905
Takumi Ichimura is an academic researcher from Prefectural University of Hiroshima. The author has contributed to research in topics: Deep learning & Deep belief network. The author has an hindex of 13, co-authored 194 publications receiving 830 citations. Previous affiliations of Takumi Ichimura include Hiroshima City University & Toin University of Yokohama.
Papers
More filters
Journal ArticleDOI
Invoking Emotions in a Dialog System based on Word-Impressions
Proceedings ArticleDOI
Density-Based Spatiotemporal Clustering Algorithm for Extracting Bursty Areas from Georeferenced Documents
Keiichi Tamura,Takumi Ichimura +1 more
TL;DR: The experimental results show that the ( ϵ,τ)-density-based spatiotemporal clustering algorithm can extract bursty areas as (ϵ, τ)- density- based spatiotsemporal clusters associated with local topics and events.
Proceedings ArticleDOI
An adaptive learning method of Deep Belief Network by layer generation algorithm
Shin Kamada,Takumi Ichimura +1 more
TL;DR: The proposed adaptive learning method of DBN can discover the optimal number of hidden neurons and weights and/or layers according to the input space during the learning.
Book ChapterDOI
An adaptive learning method of Restricted Boltzmann Machine by neuron generation and annihilation algorithm
Shin Kamada,Takumi Ichimura +1 more
TL;DR: This paper proposes the adaptive learning method of RBM that can discover an optimal number of hidden neurons according to the training situation by applying the neuron generation and annihilation algorithm.
Book ChapterDOI
Development of Coronary Heart Disease Database
TL;DR: The Coronary Heart Disease Database is developed for the purpose of evaluating prognostic systems and contains four training data-sets and one testing dataset, each of which includes more than ten thousand records related to the development of coronary heart disease.