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.

Automated Theorem Proving in Intuitionistic Propositional Logic by Deep Reinforcement Learning

no code implementations • 2 Nov 2018 • Mitsuru Kusumoto, Keisuke Yahata, Masahiro Sakai

Within the specified time limit, our prover solved 84% of the theorems in a benchmark library, while $\texttt{tauto}$ was able to solve only 52%.

Automated Theorem Proving Data Augmentation +2