分野別セミナー

Over the past decades, it has been a common practice to randomly assign the weights and biases of a neural network without any constraint, which results in poor modelling performance due to the existence of junk nodes. This talk reports our findings on the constraint condition and visually demonstrates the significance of our proposed supervisory mechanism to the performance improvement. An original, innovative and effective randomized learning algorithm and resulting randomized learner model, termed as deep stochastic configuration networks (DeepSCNs), are briefly introduced in this talk.

v
Speaker Introduction:
Reader and Associate Professor Dianhui (Justin) Wang received his PhD in 1995 from Northeastern University, China, followed by being two years postdoctoral fellow in The School of EEE at Nanyang Technological University, Singapore, and three years research fellow in the Department of Computing at The Hong Kong Polytechnic University. He joined the Department of Computer Science and Information Technology at La Trobe University in July 2001, and promoted as a Reader and Associate Professor in 2007.


Dr Wang has authored or co-authored more than 200 publications in Applied Mathematics and Computer Sciences. His working areas include machine learning and computational intelligence for data analytics, biological data mining and soft retrieval techniques. He is a senior member of IEEE, Editor-in-Chief of International Journal of Machine Intelligence and Sensory Signal Processing, Associate Editor of IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Cybernetics, Information Sciences, and Neurocomputing.