Hosei University, Graduate School

Master in Science and Engineering, Dept. of Applied Informatics • Apr, 2018 —

Hosei University

Bachelor of Science and Engineering, Dept. of Applied Informatics • Apr, 2014 — Mar, 2018


M3, Inc.

Internship • Jun, 2019 — Jul, 2019

Quantified and visualized doctors' interest from browsing history. Based on these analyses, I built a system for recommending articles for doctors from scratch.

Piascore, Inc.

Deep Learning Advisor • Jun, 2018 — Aug, 2018

I have advised how to solve practical problems of existing services that use machine learning algorithms and deep learning models. Additionally I have shown examples of the kind of problems recent deep learning models are capable of solving.

Faber Company Inc.

Internship • Mar, 27 — Mar, 29, 2018

Engineer internship 3days / ¥100,000. I implemented machine learning models that accurately capture semantic features of a document in a document similarity.

Gunosy Inc.

Internship at Dept. of Data Analysis • Mar, 2017 — Present


Teaching Assistant of hands-on training •

Taught following hands-on courses as teaching assistant:


Part-time job • Feb, 2016 — Jun, 2018

Dealt with large-scale nonstructural patent information in various forms, e.g., pre-processing, crawling, scraping, and analyzing these data.

Works Applications Co., Ltd.

Internship • Aug, 2015

Planned and implemented enterprise resource planning (ERP) packages.


International Conference

  • [1] Shunsuke Kitada, Hitoshi Iyatomi, Yoshifumi Seki. "Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creatives." Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019. (Acceptance Rate = 20%) [Preprint] [Paper] [Code]

  • [2] Shunsuke Kitada, Ryunosuke Kotani, and Hitoshi Iyatomi. "End-to-End Text Classification via Image-based Embedding using Character-level Networks." arXiv preprint arXiv:1810.03595 (2018). [Preprint] [Paper]

  • [3] Shunsuke Kitada and Hitoshi Iyatomi. "Skin lesion classification with ensemble of squeeze-and-excitation networks and semi-supervised learning." arXiv preprint arXiv:1809.02568 (2018). [Preprint]

Domestic Conference

  • [1] 北田俊輔,彌冨仁, "解釈性向上のための注意機構と損失勾配に対する関連損失の導入",NLP 若手の会 (YANS) 第 14 回シンポジウム, 2019. "奨励賞" 受賞 [Poster]

  • [2] 長澤駿太,北田俊輔,彌冨仁, "日本語の文字体系を考慮した文書分類モデルの提案",NLP 若手の会 (YANS) 第 14 回シンポジウム, 2019. [Poster]

  • [3] Daif Mahmoud, Shunsuke Kitada, Hitoshi Iyatomi, "Image Based Character Embeddings for Arabic Document Classification",NLP 若手の会 (YANS) 第 14 回シンポジウム, 2019.

  • [4] 北田俊輔, 彌冨仁, 関喜史, "広告クリエイティブ自動生成にむけたマルチタスク学習と Conditional Attention による CVR 予測", 言語処理学会第 25 回年次大会, 2019. [Paper]

  • [5] 北田俊輔, 彌冨仁, "頑健な皮膚腫瘍診断支援のための body hair augmentation", 情報処理学第 81 回会全国大会, 2019. "学生奨励賞" 受賞

  • [6] 北田俊輔, 関喜史, 彌冨仁, "広告クリエイティブ自動生成に向けた単語レベルでの評価手法の検討", NLP 若手の会 (YANS) 第 13 回シンポジウム, 2018. [Poster]

  • [7] 北田俊輔, 彌冨仁, "CE-CLCNN: Character Encoder を用いた Character-level Convolutional Neural Networks によるテキスト分類", 言語処理学会第 24 回年次大会, 2018. [Paper]

  • [8] 北田俊輔, 彌冨仁, "Character-level Convolutional Neural Networks における Wildcard Training の基礎検討", NLP 若手の会 (YANS) 第 12 回シンポジウム, 2017. [Program]



Japanese (native), English (little bit)

Programming language

Python, Go


Java, C++, C, HTML/CSS


MySQL, PostgreSQL, MongoDB


Data Science, Machine learning, Object oriented programming


Special award of FR FRONTIER: Classification of "color" of clothes in fashion images

opt DSL DeepAnalysis • Sep, 2017

Got student award using state of the art deep models.

1st prize of HackU Hosei 2018

Hack U 法政大学 2018 • Aug, 2018

Got first prize of creating ChashBox with Cpaw members.


GitHub Stars GitHub Last Commit

Maintainer • 2017 — Present

Survey of previous research and related works on machine learning (especially Deep Learning) in Japanese.

GitHub Stars GitHub Last Commit

Maintainer • 2016

Scraper for TED Talks in Python. Get talk title, transcript, talk topics and so on.


GitHub Stars GitHub Last Commit

Maintainer • 2017

Implementation of Center Loss in Chainer

GitHub Stars GitHub Last Commit

Maintainer • 2018

Implementation of IMSAT in Chainer

GitHub Stars GitHub Last Commit

Maintainer • 2018

Implementation of InceptionResNetV2 in Chainer

GitHub Stars GitHub Last Commit

Maintainer • 2018

Implementation of PyramidNet in Chainer

GitHub Stars GitHub Last Commit

Maintainer • 2018

Implementation of Xception in Chainer

GitHub Stars GitHub Last Commit

Maintainer • 2018

Implementation of Mean teachers are better role models in Chainer


CPAW: Caramel Programing Affect the World

Member • 2017 — Present

Hosei University Faculty of Engineering Soft tennis club

Member & Website maintainer • 2016 — 2018


Member • 2016 — Present

Personal traits

  • Love research and development. I am enjoying research life, and I am currently conducting three research topics simultaneously, e.g., natural language processing, medical image based computer vision,advertising technology.
  • Every day read and implement the cutting-edge deep learning models from research paper. I have released many re-implementations of models using mainly Chainer and PyTorch. Therefore, based on state-of-the-art cases, I can advise on deep learning base product design.
  • High technical communicativity. Summarize what I made and what I studied, and spread suchinformation. This shows that I can input and output regularly.