2 papers
cs.LG2018
Balanced Distribution Adaptation for Transfer Learning
Jindong Wang, Yiqiang Chen, Shuji Hao +2
Transfer learning has achieved promising results by leveraging knowledge from the source domain to annotate the target domain which has few or none labels. Existing methods often s…
cs.LG2018
An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks
Qianxiao Li, Shuji Hao
Deep learning is formulated as a discrete-time optimal control problem. This allows one to characterize necessary conditions for optimality and develop training algorithms that do…