3 papers
cs.LG2020
An Effective and Efficient Initialization Scheme for Training Multi-layer Feedforward Neural Networks
Zebin Yang, Hengtao Zhang, Agus Sudjianto +1
Network initialization is the first and critical step for training neural networks. In this paper, we propose a novel network initialization scheme based on the celebrated Stein's…
cs.LG2020
Balance-Subsampled Stable Prediction
Kun Kuang, Hengtao Zhang, Fei Wu +2
In machine learning, it is commonly assumed that training and test data share the same population distribution. However, this assumption is often violated in practice because the s…
stat.ML2019
Enhancing Explainability of Neural Networks through Architecture Constraints
Zebin Yang, Aijun Zhang, Agus Sudjianto
Prediction accuracy and model explainability are the two most important objectives when developing machine learning algorithms to solve real-world problems. The neural networks are…