2020/3/13 11:20
機械学習の主要なカンファレンスであるICLR 2020において、AIPセンターから4本の論文が採択されました。
[Accepted Papers] https://openreview.net/group?id=ICLR.cc/2020/Conference
Spotlight Presentations
- Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint
Jimmy Ba(University of Toronto/ Vector Institute)
Murat A. Erdogdu(University of Toronto/ Vector Institute)
Taiji Suzuki(University of Tokyo/ RIKEN AIP)
Denny Wu(University of Toronto/ Vector Institute/ RIKEN AIP)
Tianzong Zhang(Vector Institute/ Tsinghua University) - Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
Kenta Oono(The University of Tokyo/ Preferred Networks, Inc.)
Taiji Suzuk(The University of Tokyo/ RIKEN Center for Advanced Intelligence Project (AIP)) - Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network
Taiji Suzuki (Graduate School of Information Science and Technology, The University of Tokyo/ Center for Advanced Intelligence Project, RIKEN/ Japan Digital Design)
Hiroshi Abe (iPride Co., Ltd.)
Tomoaki Nishimura (NTT Data Corporation)
Poster Presentation
- RGBD-GAN: Unsupervised 3D Representation Learning From Natural Image Datasets via RGBD Image Synthesis
Atsuhiro Noguchi (The University of Tokyo)
Tatsuya Harada (The University of Tokyo, RIKEN)
