Zebin Yang
University of Hong Kong
31 Papers
43 Citations
Zebin Yang is an academic researcher from University of Hong Kong. The author has contributed to research in topics: Artificial neural network & Computer science. The author has an hindex of 9, co-authored 20 publications. Previous affiliations of Zebin Yang include Peking University & Beijing University of Chemical Technology.
Chat about Author
Papers
Online big data-driven oil consumption forecasting with Google trends
TL;DR: The experimental study of global oil consumption prediction confirms that the proposed online big data-driven forecasting work with Google trends improves on the traditional techniques without Google trends significantly, for both directional and level predictions.
229
Enhancing Explainability of Neural Networks Through Architecture Constraints
TL;DR: In this article, the authors proposed to enhance the explainability of neural networks through the following architecture constraints: sparse additive subnetworks, projection pursuit with orthogonality constraint, and smooth function approximation.
80
•Posted Content
GAMI-Net: An Explainable Neural Network based on Generalized Additive Models with Structured Interactions
TL;DR: Numerical experiments show that the proposed explainable GAMI-Net enjoys superior interpretability while maintaining competitive prediction accuracy in comparison to the explainable boosting machine and other benchmark machine learning models.
77
GAMI-Net: An explainable neural network based on generalized additive models with structured interactions
TL;DR: In this paper, an explainable neural network based on generalized additive models with structured interactions (GAMI-Net) is proposed to pursue a good balance between prediction accuracy and model interpretability.
74
A novel multistage deep belief network based extreme learning machine ensemble learning paradigm for credit risk assessment
Lean Yu,Zebin Yang,Ling Tang +2 more
TL;DR: The experimental study on one publicly available credit risk dataset is conducted, and the results show the superiority of the proposed multistage DBN-based ELM ensemble learning paradigm in terms of high classification accuracy.
53