15 Papers
92 Citations
Nan Zhang is an academic researcher from China University of Mining and Technology. The author has contributed to research in topics: Boltzmann machine & Restricted Boltzmann machine. The author has an hindex of 11, co-authored 15 publications. Previous affiliations of Nan Zhang include Chinese Academy of Sciences.
Chat about Author
Papers
An overview on Restricted Boltzmann Machines
TL;DR: This review aims to report the recent developments in theoretical research and applications of the Restricted Boltzmann Machine, including stochastic approximation methods, stochastically gradient methods, and preventing overfitting methods.
204
Deep Extreme Learning Machine and Its Application in EEG Classification
Shifei Ding,Shifei Ding,Nan Zhang,Nan Zhang,Xinzheng Xu,Xinzheng Xu,Guo Lili,Guo Lili,Jian Zhang,Jian Zhang +9 more
TL;DR: Effectiveness of the application of DELM in EEG classification is confirmed and it is confirmed that MLELM approximate the complicated function but it also does not need to iterate during the training process.
Twin support vector machine: theory, algorithm and applications
TL;DR: The current state of the theoretical research and practical advances on TWSVM are reported, mainly including least squares twin support vector machine, smooth twin support vectors machine, regularized twin supportvector machine, projection twin support Vector machine, and modified TWS VM on the model selection problem.
95
Unsupervised extreme learning machine with representational features
Shifei Ding,Shifei Ding,Nan Zhang,Nan Zhang,Jian Zhang,Jian Zhang,Xinzheng Xu,Xinzheng Xu,Zhongzhi Shi +8 more
TL;DR: The proposed unsupervised extreme learning machine based on embedded features of ELM-AE (US-EF-ELM) algorithm applies ELm-AE to US- ELM, which gives favorable performance compared to state-of-the-art clustering algorithms.
79
Multi layer ELM-RBF for multi-label learning
Nan Zhang,Shifei Ding,Jian Zhang +2 more
- 01 Jun 2016
TL;DR: A neural network derived from radial basis function for multi-label learning (ML-RBF) and WuELM-AE is proposed, which achieves satisfactory results on single-label and multi- label data sets.
58