A paper entitled Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding was featured by NIKKEI XTECH.
This paper was accepted at the International Conference on Machine Learning (ICML) 2021, a major conference on Artificial Intelligence (July 18-24, 2021, Online).
- Quantitative Understanding of VAE as a Non-linearly Scaled Isometric Embedding
Akira Nakagawa (Fujitsu Laboratories Ltd.)
Keizo Kato (Fujitsu Laboratories Ltd.)
Taiji Suzuki (The University of Tokyo / RIKEN AIP)
*The article may be found at the link below.
(Viewing the full article requires a Nikkei user account.)
*Available only in Japanese