3 papers
stat.ML2021
Statistical Mechanical Analysis of Catastrophic Forgetting in Continual Learning with Teacher and Student Networks
Haruka Asanuma, Shiro Takagi, Yoshihiro Nagano +3
When a computational system continuously learns from an ever-changing environment, it rapidly forgets its past experiences. This phenomenon is called catastrophic forgetting. While…
quant-ph2020
Minor-embedding heuristics for large-scale annealing processors with sparse hardware graphs of up to 102,400 nodes
Yuya Sugie, Yuki Yoshida, Normann Mertig +7
Minor embedding heuristics have become an indispensable tool for compiling problems in quadratically unconstrained binary optimization (QUBO) into the hardware graphs of quantum an…
stat.ML2020
Data-Dependence of Plateau Phenomenon in Learning with Neural Network --- Statistical Mechanical Analysis
Yuki Yoshida, Masato Okada
The plateau phenomenon, wherein the loss value stops decreasing during the process of learning, has been reported by various researchers. The phenomenon is actively inspected in th…