Wing of South China University of Technology, China

Neural networks are widely applied in many different applications. However, current neural network training methods rely on the manual selection of architectures and parameters selected based on the minimization of training errors. The ultimate goal of training is to find a neural network that generalizes knowledge in training dataset to future unseen situations. Given this goal, a Localized Generalization Error Model is proposed to automatically find architectures and parameters for different types of neural networks. This method has been applied to diversified applications: for instances pattern classification, smart grid, image retrieval, and smart home.

Biography:

Prof. Wing W. Y. Ng is a Professor with the School of Computer Science and Engineering, South China University of Technology and the Deputy Director of the Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information. His major research interests include machine learning in non-stationary environments, medical imaging, multimedia retrieval, smart home, and AI security. These works have been published in IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cybernetics, IEEE Transactions on Industrial Informatics, IEEE Transactions on Multimedia, Pattern Recognition, etc. He is the PI of five China National Natural Science Foundation projects and a Program for New Century Excellent Talents in University from China Ministry of Education. Prof. Ng is currently an associate editor of the International Journal of Machine Learning and Cybernetics. He is an IEEE senior member and served as the Board of Governor of the IEEE Systems, Man and Cybernetics Society (SMCS) in 2011 - 2013.