MAEDA, Iwao
Second year PhD Student
Second year PhD Student
Research theme:
Research theme:
- Uncertainty consideration of neural networks
- Short term market trend prediction
Career
- 2012-2016 Department of Chemical System Engineering, Faculty of Engineering, The University of Tokyo, bachelor's degree.
- 2016-2018 Department of Chemistry System Engineering, Graduate School of Engineering, The University of Tokyo, master's degree.
- 2018- Izumi Laboratory, Department of Systems Innovation, Graduate School of Engineering, The University of Tokyo, ph.D.
Interests
- Bayesian deep learning
- Predictive uncertainty, out-of-distribution detection
- Academic education
Favorites
- Volleyball
- Ramen
- Alcohol (beer, gin)
- Video games (Pokemon, Splatoon)
Publications
- Paper
- Maeda, I., Hasegawa, K., Kaneko, H., Funatsu, K. Novel Method Proposing Chemical Structures with Desirable Profile of Activities Based on Chemical and Protein Spaces. Molecular Informatics, 36(12) (2017)
- Conferences
- Maeda, I., Kaneko, H., Funatsu, K. Visualization of chemical space and protein space considering compound-protein interaction, In: The 44th Symposium on Structure-Activity Relationship, pp. 25-28 (2016)
- Maeda, I., Matsushima, H., Sakaji, H., Izumi, K., deGraw, D., Tomioka, H., Kato, A., Short-time market trend prediction by considering time series of high frequency order. In: SigFin21, (2018)
- Maeda, I., Matsushima, H., Sakaji, H., Izumi, K., deGraw, D., Tomioka, H., Kato, A., Kitano, M., Learning Uncertainty in Market Trend Forecast Using Bayesian Neural Networks. In: International Conference on Decision Economics (DECON), (2019)
- Maeda, I., Matsushima, H., Sakaji, H., Izumi, K., deGraw, D., Tomioka, H., Kato, A., Kitano, Importance of Uncertainty Estimation in Deep Learning. In: The 33rd Annual Conference of the Japanese Society for Artificial Intelligence , (2019)
3. Announcement
- Maeda, I., Yuge, N., Watanabe, T., Sugawara, Y., Miuchi, N., 実測値の不確かさを考慮した活性予測モデル構築によるSirtuin1 阻害剤探索. In: The 4th AIDD contest, (2017)
- Indo, S., Maeda, I., Kitagawa, K., Fujita, K., Shimono, T., Deep Quoridor. In: Deep Learning Day, (2017)
4. Others
- SAR Presentation Award In: 44th Symposium on Structure-Activity Relationship, (2016)
- Student Award In: The 4th AIDD contest, (2017)
- Poster Award In: Deep Learning Day, (2017)
Contact: d2018imaeda[at]socsim.org
Contact: d2018imaeda[at]socsim.org