Evolutionary optimization of model merging recipes T Akiba, M Shing, Y Tang, Q Sun, D Ha arXiv preprint arXiv:2403.13187, 2024 | 2 | 2024 |
Prediction of tissue-of-origin of early stage cancers using serum miRNomes J Matsuzaki, K Kato, K Oono, N Tsuchiya, K Sudo, A Shimomura, ... JNCI Cancer Spectrum 7 (1), pkac080, 2023 | 8 | 2023 |
Hyperparameter tuning method, program trial system, and computer program S Sano, T Yanase, T Ohta, T Akiba US Patent App. 17/643,661, 2022 | 1 | 2022 |
Hyperparameteroptimierungsverfahren, Programmversuchssystem und Computerprogramm S Sano, T Yanase, T Ohta, T Akiba | | 2022 |
Hyperparameter tuning method, device, and program T Akiba US Patent App. 17/221,060, 2021 | 2 | 2021 |
MN-Core-A Highly Efficient and Scalable Approach to Deep Learning K Namura, JM Kühn, T Adachi, H Imachi, H Kaneko, T Kato, G Watanabe, ... 2021 Symposium on VLSI Circuits, 1-2, 2021 | 2 | 2021 |
Online-Codistillation Meets LARS, Going beyond the Limit of Data Parallelism in Deep Learning S Murai, H Mikami, M Koyama, S Suzuki, T Akiba 2020 IEEE/ACM Fourth Workshop on Deep Learning on Supercomputers (DLS), 1-9, 2020 | | 2020 |
DEVICE, METHOD AND PROGRAM FOR DETERMINING DISEASE DEVELOPMENT D OKANOHARA, O Kenta, N Ota, K Hamzaoui, T Akiba | | 2020 |
Shakedrop regularization for deep residual learning Y Yamada, M Iwamura, T Akiba, K Kise IEEE Access 7, 186126-186136, 2019 | 165 | 2019 |
Team PFDet's Methods for Open Images Challenge 2019 Y Niitani, T Ogawa, S Suzuki, T Akiba, T Kerola, K Ozaki, S Sano arXiv preprint arXiv:1910.11534, 2019 | 3 | 2019 |
Disease affection determination device, disease affection determination method, and disease affection determination program D Okanohara, O Kenta, N Ota, K Hamzaoui, T Akiba US Patent App. 16/346,017, 2019 | 3 | 2019 |
Chainer: A deep learning framework for accelerating the research cycle S Tokui, R Okuta, T Akiba, Y Niitani, T Ogawa, S Saito, S Suzuki, ... Proceedings of the 25th ACM SIGKDD International Conference on Knowledge …, 2019 | 155 | 2019 |
Optuna: A next-generation hyperparameter optimization framework T Akiba, S Sano, T Yanase, T Ohta, M Koyama Proceedings of the 25th ACM SIGKDD international conference on knowledge …, 2019 | 4391 | 2019 |
Gradient compressing apparatus, gradient compressing method, and non-transitory computer readable medium Y Tsuzuku, H Imachi, T Akiba US Patent App. 16/171,340, 2019 | 4 | 2019 |
Image processing system and image processing unit for generating attack image T Akiba US Patent App. 16/169,949, 2019 | 1 | 2019 |
A graph theoretic framework of recomputation algorithms for memory-efficient backpropagation M Kusumoto, T Inoue, G Watanabe, T Akiba, M Koyama Advances in Neural Information Processing Systems 32, 2019 | 43 | 2019 |
Sampling techniques for large-scale object detection from sparsely annotated objects Y Niitani, T Akiba, T Kerola, T Ogawa, S Sano, S Suzuki Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2019 | 37 | 2019 |
Pfdet: 2nd place solution to open images challenge 2018 object detection track T Akiba, T Kerola, Y Niitani, T Ogawa, S Sano, S Suzuki arXiv preprint arXiv:1809.00778, 2018 | 25 | 2018 |
Distributed deep learning device and distributed deep learning system T Akiba US Patent App. 15/879,168, 2018 | 2 | 2018 |
Variance-based gradient compression for efficient distributed deep learning Y Tsuzuku, H Imachi, T Akiba arXiv preprint arXiv:1802.06058, 2018 | 73 | 2018 |