Search Results for author: Gentaro Watanabe

Found 2 papers, 1 papers with code

A Graph Theoretic Framework of Recomputation Algorithms for Memory-Efficient Backpropagation

3 code implementations NeurIPS 2019 Mitsuru Kusumoto, Takuya Inoue, Gentaro Watanabe, Takuya Akiba, Masanori Koyama

Recomputation algorithms collectively refer to a family of methods that aims to reduce the memory consumption of the backpropagation by selectively discarding the intermediate results of the forward propagation and recomputing the discarded results as needed.

A Deep-Learning Approach for Operation of an Automated Realtime Flare Forecast

no code implementations6 Jun 2016 Yuko Hada-Muranushi, Takayuki Muranushi, Ayumi Asai, Daisuke Okanohara, Rudy Raymond, Gentaro Watanabe, Shigeru Nemoto, Kazunari Shibata

Automated forecasts serve important role in space weather science, by providing statistical insights to flare-trigger mechanisms, and by enabling tailor-made forecasts and high-frequency forecasts.

Cannot find the paper you are looking for? You can Submit a new open access paper.