| Title | Meta-Cognitive Cognitive Neural Networks in Medical Informatics and Control |
| Speaker | Dr. Suresh Sundaram |
| Chair | Wlodzislaw Duch |
Abstract
Within this elaboration a generic learning algorithm, subsequently referred as Meta-cognitiver Cognitive Neural Network (McNN), applying higher order intelligence for effective learning in the field of artificial neural networks, is being introduced. Currently, available effectiveness learning algorithms in neural network are usually depends on user expertise in selecting appropriate samples and order of presentation, in contrary to the introduced one. The learning algorithm in McNN does not depends on the user expertise, it selects appropriate samples based on its own current knowledge and also select appropriate learning strategies to capture the knowledge present in the sample on-the-go. This Meta-cognitive Neural Network (McNN) has two components, namely the cognitive component and the meta-cognitive component. A radial basis function network is the fundamental building block of the cognitive component. The meta-cognitive component controls the learning process in the cognitive component by deciding what-to-learn, when-to-learn and how-to-learn. When a sample is presented at the cognitive component of McNN, the meta-cognitive component chooses the best learning strategy for the sample using estimated class label, maximum hinge error, confidence of classifier and class-wise significance. Also sample overlapping conditions are considered in growth strategy for proper initialization of new hidden neurons. Finally, we provide an outline of the proposed McNN in practical Medical informatics problems and intelligent control problems.
Biography
Suresh Sundaram received his B.E. in Electrical and Electronics Engineering from Bharathiyar University, and his M.E. and Ph.D. degrees from Indian Institute of Science Bangalore, India. He was a post-doctoral researcher in the School of Electrical Engineering, Nanyang Technological University, Singapore, from 2005-2007. Subsequently, he was selected as a ERCIM research fellow for the period of 2007-2008 and he spent valuable time in the project team PULSAR at INRIA Sophia-Antipolis, France. For a short period, he was working as Faculty at Industrial Engineering, Korea University, Seoul. Later, he was with Indian Institute of Technology, Delhi, as an Assistant Professor in Electrical Engineering from 2008-2009. Since 2010 he has been working as an Assistant Professor in the School of Computer Engineering, Nanyang Technological University, Singapore. He has published more than 100 journal/conference papers and a book on Supervised Learning with Complex-valued Neural Networks.
Website: www.ntu.edu.sg/home/ssundaram
