H
Hong Qiao
Researcher at Chinese Academy of Sciences
Publications - 385
Citations - 6301
Hong Qiao is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Artificial neural network & Support vector machine. The author has an hindex of 36, co-authored 362 publications receiving 4976 citations. Previous affiliations of Hong Qiao include City University of Hong Kong & University of Manchester.
Papers
More filters
Journal ArticleDOI
On stabilization of bilinear uncertain time-delay stochastic systems with Markovian jumping parameters
TL;DR: This work focuses on the design of a robust state-feedback controller such that, for all admissible uncertainties as well as nonlinear disturbances, the closed-loop system is stochastically exponentially stable in the mean square, independent of the time delay.
Journal ArticleDOI
Event-Triggered State Estimation for Discrete-Time Multidelayed Neural Networks With Stochastic Parameters and Incomplete Measurements
Bo Shen,Zidong Wang,Hong Qiao +2 more
TL;DR: An event-triggered state estimator is constructed and a sufficient condition is given under which the estimation error dynamics is exponentially ultimately bounded in the mean square, and the characterization of the desired estimator gain is designed in terms of the solution to a certain matrix inequality.
Journal ArticleDOI
Discriminatively Boosted Image Clustering with Fully Convolutional Auto-Encoders
TL;DR: This paper first introduces fully convolutional auto-encoders for image feature learning and then proposes a unified clustering framework to learn image representations and cluster centers jointly based on a fully Convolutional Auto-encoder and soft k-means scores.
Journal ArticleDOI
Nonlinear measures: a new approach to exponential stability analysis for Hopfield-type neural networks
Hong Qiao,Jigen Peng,Zongben Xu +2 more
TL;DR: A novel approach for stability analysis of neural networks is developed with a new concept called nonlinear measure introduced to quantify stability of nonlinear systems in the way similar to the matrix measure for stability of linear systems.
Journal ArticleDOI
A reference model approach to stability analysis of neural networks
TL;DR: A novel methodology called a reference model approach to stability analysis of neural networks is proposed, to study a neural network model with reference to other related models, so that different modeling approaches can be combinatively used and powerfully cross-fertilized.