Sotetsu Koyamada

産業技術総合研究所 / リサーチ・アシスタント

東京都中央区

Sotetsu Koyamada

産業技術総合研究所 / リサーチ・アシスタント

東京都中央区

Sotetsu Koyamada

産業技術総合研究所 / リサーチ・アシスタント

This user is using the new profile.

Join our Beta test to try out our new profile.

Join

人間万事塞翁が馬

最新の状況についてはCVを参照してください。 CV: https://sotets.uk/cv 2018年11月現在、新しいポジションは探しておりません。

Aug 2016
-
Present

リサーチ・アシスタント
Present

Present

Aug 2016 -

Present

Apr 2015
-
Present
Present

Apr 2015 -

Present

機械学習エンジニア

Oct 2013
-
Mar 2015

リサーチ・インターンシップ

Oct 2013 - Mar 2015

脳機能画像解析・機械学習

Mar 2015

京都大学大学院(修士課程)

情報学研究科システム科学専攻

Mar 2015

石井信研究室

Mar 2013

京都大学

経済学部経済学科

Mar 2013

飯山将晃ゼミ

京都大学大学院(博士課程)

情報学研究科システム科学専攻
Present

Present

Present

石井信研究室(在学中)

修士論文: Principal Sensitivity Analysis and Its Application to Knowledge Discovery in Functional Neuroimaging

In this thesis, we studied methods to visualize the knowledge captured by supervised classifiers. In particular, we developed a new method, “Principal Sensitivity Analysis (PSA),” to analyze the sensitivity of the trained classifier. In PSA, principal sensitivity map (PSM) is defined as the direction in the input space to which the classifier is most sensitive, and k-th PSM is also analogously defined for each k. Using these maps, PSA decomposes the input space based on the sensitivity of the classifier. As a primitive case study, we first applied the PSA to the classifier trained for digit classification. We were able to find a direct association between the PSMs and the discriminative features of the digits that we humans intuitively use for classification. Next, in order to assess the performance of our algorithm on nonlinear and hierarchical classifiers in a practical setting, we applied the PSA to the deep neural network (DNN) trained with large-scale neuroimaging database. We confirmed that, in comparison to other baseline methods, the DNN can capture richer discriminative features of brain activities that are common to many human subjects. Interestingly, we were able to find nontrivial connections between the PSMs of the trained DNN and the functional connectivity among brain areas, a phenomenon studied in neuroscience. This suggests a relation between the discriminative features of brain activities and the functional connectivity among brain areas, a phenomenon studied in neuroscience. This suggests a relation between the discriminative features of brain activities and the functional connectivity.

修士論文: Principal Sensitivity Analysis and Its Application to Knowledge Discovery in Functional Neuroimaging

In this thesis, we studied methods to visualize the knowledge captured by supervised classifiers. In particular, we developed a new method, “Principal Sensitivity Analysis (PSA),” to analyze the sensitivity of the trained classifier. In PSA, principal sensitivity map (PSM) is defined as the direction in the input space to which the classifier is most sensitive, and k-th PSM is also analogously defined for each k. Using these maps, PSA decomposes the input space based on the sensitivity of the classifier. As a primitive case study, we first applied the PSA to the classifier trained for digit classification. We were able to find a direct association between the PSMs and the discriminative features of the digits that we humans intuitively use for classification. Next, in order to assess the performance of our algorithm on nonlinear and hierarchical classifiers in a practical setting, we applied the PSA to the deep neural network (DNN) trained with large-scale neuroimaging database. We confirmed that, in comparison to other baseline methods, the DNN can capture richer discriminative features of brain activities that are common to many human subjects. Interestingly, we were able to find nontrivial connections between the PSMs of the trained DNN and the functional connectivity among brain areas, a phenomenon studied in neuroscience. This suggests a relation between the discriminative features of brain activities and the functional connectivity among brain areas, a phenomenon studied in neuroscience. This suggests a relation between the discriminative features of brain activities and the functional connectivity.


Skills and qualities

機械学習

Recommended by Daichi Katayama and 6 more
7

データマイニング

Recommended by Daichi Katayama and 5 more
6

統計モデリング

Recommended by Daichi Katayama and 5 more
6

Python

Recommended by Daichi Katayama and 3 more
4

Go

0

Git, Scala, Google Cloud Platform

Publications

きっかけは優秀な同期との出会い データ解析者の卵がリクルートに入社した理由

Apr 2016

技術が進化した時代にどう生き残る?  1年目社員が学びの場を作り出した理由

Apr 2016

KDD2015に参加してきました

Sept 2015

Accomplishments/Portfolio

速習 強化学習 ―基礎理論とアルゴリズム―

Neural sequence model training via α-divergence minimization

Principal sensitivity analysis

修士論文: Principal Sensitivity Analysis and Its Application to Knowledge Discovery in Functional Neuroimaging

Construction of subject-independent brain decoders for human fMRI with deep learning


Languages

Japanese - Native, English - Conversational