S
Shingo Horiuchi
Researcher at NTT DATA
Publications - 5
Citations - 44
Shingo Horiuchi is an academic researcher from NTT DATA. The author has contributed to research in topics: Deep learning & Curse of dimensionality. The author has an hindex of 3, co-authored 5 publications receiving 26 citations.
Papers
More filters
Posted Content
Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error
Taiji Suzuki,Hiroshi Abe,Tomoya Murata,Shingo Horiuchi,Kotaro Ito,Tokuma Wachi,So Hirai,Masatoshi Yukishima,Tomoaki Nishimura +8 more
TL;DR: A new theoretical framework for model compression is developed and a new pruning method called spectral pruning is proposed based on this framework, which defines the ``degrees of freedom'' to quantify the intrinsic dimensionality of a model by using the eigenvalue distribution of the covariance matrix across the internal nodes.
Posted Content
Spectral-Pruning: Compressing deep neural network via spectral analysis
Taiji Suzuki,Hiroshi Abe,Tomoya Murata,Shingo Horiuchi,Kotaro Ito,Tokuma Wachi,So Hirai,Masatoshi Yukishima,Tomoaki Nishimura +8 more
TL;DR: This work develops a new theoretical frame-work for model compression, and proposes a new method called Spectral-Pruning based on the theory, which makes use of both "input" and "output" in each layer and is easy to implement.
Proceedings ArticleDOI
Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error.
Taiji Suzuki,Hiroshi Abe,Tomoya Murata,Shingo Horiuchi,Kotaro Ito,Tokuma Wachi,So Hirai,Masatoshi Yukishima,Tomoaki Nishimura +8 more
TL;DR: In this article, a new theoretical framework for model compression and a new pruning method called spectral pruning is proposed to quantify the intrinsic dimensionality of a model by using the eigenvalue distribution of the covariance matrix across the internal nodes and show that the compression ability is essentially controlled by this quantity.
Proceedings ArticleDOI
Automatic image description by using word-level features
TL;DR: This paper proposes a novel approach to collect general phrases for generating image descriptions based on the assumption that there are high frequency phrases related to an query image in the image descriptions of similar images.
Proceedings ArticleDOI
Model-based Data-Complexity Estimator for Deep Learning Systems
TL;DR: In this paper, the authors propose a method of evaluating a complexity of an input without a label for a given trained model for analyzing a dataset to find inputs unfamiliar to the model and estimating the similarity between two datasets.