Yasufumi Sakai

According to our database, Yasufumi Sakai authored at least 18 papers between 2014 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

Active Learning for Graph Neural Networks Training in Catalyst Energy Prediction.

Yasufumi Sakai, Naoki Matsumura, Atsuki Inoue, Hiroshi Kawaguchi, Thang Dang, Atsushi Ishikawa, Árni Björn Höskuldsson, Egill Skúlason

Proceedings of the International Joint Conference on Neural Networks, 2024

2023

Self-Supervised Learning with Atom Replacement for Catalyst Energy Prediction by Graph Neural Networks.

Yasufumi Sakai, Thang Dang, Shigeki Fukuta, Koichi Shirahata, Atsushi Ishikawa, Atsuki Inoue, Hiroshi Kawaguchi, Árni Björn Höskuldsson, Egill Skúlason

Proceedings of the International Neural Network Society Workshop on Deep Learning Innovations and Applications, 2023

Semilayer-Wise Partial Quantization Without Accuracy Degradation or Back Propagation.

Tomoya Matsuda, Kengo Matsumoto, Atsuki Inoue, Hiroshi Kawaguchi, Yasufumi Sakai

Proceedings of the Artificial Neural Networks and Machine Learning - ICANN 2023, 2023

A Mixed-Precision Quantization Method without Accuracy Degradation Using Semilayers.

Kengo Matsumoto, Tomoya Matsuda, Atsuki Inoue, Hiroshi Kawaguchi, Yasufumi Sakai

Proceedings of the Asian Conference on Machine Learning, 2023

2022

Structured Pruning with Automatic Pruning Rate Derivation for Image Processing Neural Networks.

Yasufumi Sakai, Akinori Iwakawa, Tsuguchika Tabaru

Proceedings of the ISMSI 2022: 6th International Conference on Intelligent Systems, Metaheuristics & Swarm Intelligence, Seoul, Republic of Korea, April 9, 2022

Automatic Pruning Rate Derivation for Structured Pruning of Deep Neural Networks.

Yasufumi Sakai, Akinori Iwakawa, Tsuguchika Tabaru, Atsuki Inoue, Hiroshi Kawaguchi

Proceedings of the 26th International Conference on Pattern Recognition, 2022

Channel-wise quantization without accuracy degradation using Δloss analysis.

Kazuki Okado, Kengo Matsumoto, Atsuki Inoue, Hiroshi Kawaguchi, Yasufumi Sakai

Proceedings of the ICMLT 2022: 7th International Conference on Machine Learning Technologies, Rome, Italy, March 11, 2022

Regularizing Data for Improving Execution Time of NLP Model.

Thang Dang, Yasufumi Sakai, Tsuguchika Tabaru, Akihiko Kasagi

Proceedings of the Thirty-Fifth International Florida Artificial Intelligence Research Society Conference, 2022

2021

A High-Speed Neural Architecture Search Considering the Number of Weights.

Fuyuka Yamada, Satoki Tsuji, Hiroshi Kawaguchi, Atsuki Inoue, Yasufumi Sakai

Proceedings of the KI 2021: Advances in Artificial Intelligence - 44th German Conference on AI, Virtual Event, September 27, 2021

Efficient and Large Scale Pre-training Techniques for Japanese Natural Language Processing.

Akihiko Kasagi, Masahiro Asaoka, Akihiro Tabuchi, Yosuke Oyama, Takumi Honda, Yasufumi Sakai, Thang Dang, Tsuguchika Tabaru

Proceedings of the Ninth International Symposium on Computing and Networking, 2021

Greedy Search Algorithm for Mixed Precision in Post-Training Quantization of Convolutional Neural Network Inspired by Submodular Optimization.

Satoki Tsuji, Hiroshi Kawaguchi, Atsuki Inoue, Yasufumi Sakai, Fuyuka Yamada

Proceedings of the Asian Conference on Machine Learning, 2021

2019

Dropout and DropConnect for Reliable Neuromorphic Inference Under Communication Constraints in Network Connectivity.

Yasufumi Sakai, Bruno U. Pedroni, Siddharth Joshi, Satoshi Tanabe, Abraham Akinin, Gert Cauwenberghs

IEEE J. Emerg. Sel. Topics Circuits Syst., 2019

Neural-network assistance to calculate precise eigenvalue for fitness evaluation of real product design.

Yukito Tsunoda, Takahiro Notsu, Yasufumi Sakai, Naoki Hamada, Toshihiko Mori, Teruo Ishihara, Atsuki Inoue

Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2019

DropOut and DropConnect for Reliable Neuromorphic Inference under Energy and Bandwidth Constraints in Network Connectivity.

Yasufumi Sakai, Bruno U. Pedroni, Siddharth Joshi, Abraham Akinin, Gert Cauwenberghs

Proceedings of the IEEE International Conference on Artificial Intelligence Circuits and Systems, 2019

2016

A 28.3 Gb/s 7.3 pJ/bit 35 dB backplane transceiver with eye sampling phase adaptation in 28 nm CMOS.

Hiroki Miyaoka, Futoshi Terasawa, Masahiro Kudo, Hideki Kano, Atsushi Matsuda, Noriaki Shirai, Shigeaki Kawai, Takayuki Shibasaki, Takumi Danjo, Yuuki Ogata, Yasufumi Sakai, Hisakatsu Yamaguchi, Toshihiko Mori, Yoichi Koyanagi, Hirotaka Tamura, Yutaka Ide, Kazuhiro Terashima, Hirohito Higashi, Tomokazu Higuchi, Naoaki Naka

Proceedings of the 2016 IEEE Symposium on VLSI Circuits, 2016

3.5 A 56Gb/s NRZ-electrical 247mW/lane serial-link transceiver in 28nm CMOS.

Takayuki Shibasaki, Takumi Danjo, Yuuki Ogata, Yasufumi Sakai, Hiroki Miyaoka, Futoshi Terasawa, Masahiro Kudo, Hideki Kano, Atsushi Matsuda, Shigeaki Kawai, Tomoyuki Arai, Hirohito Higashi, Naoaki Naka, Hisakatsu Yamaguchi, Toshihiko Mori, Yoichi Koyanagi, Hirotaka Tamura

Proceedings of the 2016 IEEE International Solid-State Circuits Conference, 2016

2014

A 1.95 GHz Fully Integrated Envelope Elimination and Restoration CMOS Power Amplifier Using Timing Alignment Technique for WCDMA and LTE.

Kazuaki Oishi, Eiji Yoshida, Yasufumi Sakai, Hideki Takauchi, Yoichi Kawano, Noriaki Shirai, Hideki Kano, Masahiro Kudo, Tomotoshi Murakami, Tetsuro Tamura, Shigeaki Kawai, Kazuo Suto, Hiroshi Yamazaki, Toshihiko Mori

IEEE J. Solid State Circuits, 2014

3.2 A 1.95GHz fully integrated envelope elimination and restoration CMOS power amplifier with envelope/phase generator and timing aligner for WCDMA and LTE.

Kazuaki Oishi, Eiji Yoshida, Yasufumi Sakai, Hideki Takauchi, Yoichi Kawano, Noriaki Shirai, Hideki Kano, Masahiro Kudo, Tomotoshi Murakami, Tetsuro Tamura, Seitaro Kawai, Shinji Yamaura, Kazuo Suto, Hiroshi Yamazaki, Toshihiko Mori

Proceedings of the 2014 IEEE International Conference on Solid-State Circuits Conference, 2014