Takumi Nakagawa

Publication Activity (10 Years)

Years Active: 2022-2024
Publications (10 Years): 6

Top Topics

Cosine Similarity

Numerical Simulations

Supervised Learning

Top Venues

Neural Networks

Publications

Hiroo Irobe, Wataru Aoki, Kimihiro Yamazaki, Yuhui Zhang, Takumi Nakagawa, Hiroki Waida, Yuichiro Wada, Takafumi Kanamori
Robust VAEs via Generating Process of Noise Augmented Data. CoRR (2024)
Takumi Nakagawa, Yutaro Sanada, Hiroki Waida, Yuhui Zhang, Yuichiro Wada, Kosaku Takanashi, Tomonori Yamada, Takafumi Kanamori
Denoising cosine similarity: A theory-driven approach for efficient representation learning. Neural Networks 169 (2024)
Takumi Nakagawa, Yutaro Sanada, Hiroki Waida, Yuhui Zhang, Yuichiro Wada, Kosaku Takanashi, Tomonori Yamada, Takafumi Kanamori
Denoising Cosine Similarity: A Theory-Driven Approach for Efficient Representation Learning. CoRR (2023)
Hiroki Waida, Yuichiro Wada, Léo Andéol, Takumi Nakagawa, Yuhui Zhang, Takafumi Kanamori
Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis. CoRR (2023)
Hiroki Waida, Yuichiro Wada, Léo Andéol, Takumi Nakagawa, Yuhui Zhang, Takafumi Kanamori
Towards Understanding the Mechanism of Contrastive Learning via Similarity Structure: A Theoretical Analysis. ECML/PKDD (4) (2023)
Yutaro Sanada, Takumi Nakagawa, Yuichiro Wada, Kosaku Takanashi, Yuhui Zhang, Kiichi Tokuyama, Takafumi Kanamori, Tomonori Yamada
Deep Self-Supervised Learning of Speech Denoising from Noisy Speeches. INTERSPEECH (2022)