Z
Zhi-Hua Zhou
Researcher at Nanjing University
Publications - 633
Citations - 64307
Zhi-Hua Zhou is an academic researcher from Nanjing University. The author has contributed to research in topics: Semi-supervised learning & Artificial neural network. The author has an hindex of 102, co-authored 626 publications receiving 52850 citations. Previous affiliations of Zhi-Hua Zhou include Michigan State University & Tokyo Institute of Technology.
Papers
More filters
Proceedings ArticleDOI
Rank Consistency based Multi-View Learning: A Privacy-Preserving Approach
TL;DR: The proposed RANC framework provides a privacy-preserving way for multi-view learning by converting predicted values of each view into an Accumulated Prediction Matrix (APM) with low-rank constraint enforced jointly by the multiple views.
Posted Content
Handling Concept Drift via Model Reuse
TL;DR: In this paper, a model reuse approach is proposed to handle concept drift via model reuse, leveraging previous knowledge by reusing models each model is associated with a weight representing its reusability towards current data, and the weight is adaptively adjusted according to the model performance.
Proceedings ArticleDOI
Using neural networks for fault diagnosis
TL;DR: A universal fault instance model is proposed, which aims to solve problems existing in the present technology of fault diagnosis, such as the lack of universality, the difficulty in the use of real time systems and the dilemma of stability and plasticity.
Posted Content
Multi-View Active Learning in the Non-Realizable Case
Wei Wang,Zhi-Hua Zhou +1 more
TL;DR: It is proved that, with unbounded Tsybakov noise, the sample complexity of multi-view active learning can be O(log 1/e), contrasting to single-view setting where the polynomial improvement is the best possible achievement.
Proceedings Article
Labeling complicated objects: multi-view multi-instance multi-label learning
TL;DR: A multi-view MIML framework based on hierarchical Bayesian Network is developed, and an effective learning algorithm based on variational inference is derived that can effectively handle datasets with a large number of labels.