Professor Asim Roy
Asim Roy, Ph.D.
is Professor of Information Systems at Arizona State University. He
earned his B.E. in Mechanical Engineering from Calcutta University,
India, his M.S. in Operations Research from Case Western Reserve
Cleveland, Ohio, and his Ph.D. in Operations Research from the
Texas at Austin. He also studied Industrial Engineering at Rutgers
University, New Brunswick, New Jersey. He has been a Visiting Scholar at
Stanford University, visiting Professor David Rumelhart in the
Department, and a Visiting Scientist at the Robotics and Intelligent
Systems Group at Oak Ridge National Laboratory, Oak Ridge, Tennessee.
Asim is on the Governing Board of the International Neural Network Society (INNS), founder of the INNS Section on Autonomous Learning and Guest Editor-in-Chief of a special issue of Neural Networks on autonomous learning. He also serves on the editorial boards of Neural Networks and Neural Information Processing — Letters and Reviews. He has been the Letters Editor of IEEE Transactions on Neural Networks and has served on the organizing committees of many scientific conferences. He was the Program Chair for the ORSA/TIMS (Operations Research Society of America / The Institute of Management Sciences) National meeting in Las Vegas and the General Chair of the ORSA/TIMS National meeting in Phoenix. Asim is listed in Who’s Who in America.
His research interests are in theories of the brain, brain-like learning, neural networks, machine learning, data mining, pattern recognition, prediction and forecasting, intelligent systems, and nonlinear multiple objective optimization. His research has been published in Management Science, Decision Sciences, Mathematical Programming, Financial Management, Neural Networks, Neural Computation, Naval Research Logistics, ORSA Journal on Computing, IEEE Transactions on Neural Networks, IEEE Transactions on Fuzzy Systems, IEEE Transactions on Systems, Man and Cybernetics, and other journals.
Asim designed and developed the software system IFPS/OPTIMUM that pioneered the idea of incorporating optimization tools in financial and planning languages for managerial use. It has been used by hundreds of corporations worldwide for financial, corporate, and production planning. The system has saved many companies hundreds of millions of dollars. Following in its footsteps, such optimization systems are now widely available with spreadsheet systems such as Excel Solver within Excel.
Asim recently published a theory of the brain that postulates that localist representation, as opposed to distributed representation, is used widely in the brain. That implies that firings of neurons in the brain have “meaning and interpretation” on a stand-alone basis. In 2008, Asim published a theory of the brain that postulates that there are parts of the brain that control other parts and thus control theoretic principles can be used to design and construct systems similar to the brain. These theories invalidate many ideas of the current dominant theory of the brain called “connectionism”. Asim’s work has been described as pioneering by distinguished scholars in the field. He has been invited to many national and international conferences for plenary talks and for tutorials, workshops, and short courses on his new learning theory and methods.
Asim authored Connectionism, controllers, and a brain theory, The hardest test for a theory of cognition: The Input Test, On Connectionism, Rule Extraction and Brain-like Learning, and Artificial Neural Networks — A Science in Trouble and coauthored An Interactive Weight Space Reduction Procedure for Nonlinear Multiple Objective Mathematical Programming, A Multi-Tasking Learning Model for Online Pattern Recognition, An Interactive Search Method Based on User Preferences, A Neural Network Learning Theory and a Polynomial Time RBF Algorithm, An algorithm to generate radial basis function (RBF)-like nets for classification problems, A polynomial time algorithm for the construction and training of a class of multilayer perceptrons, A Polynomial Time Algorithm for Generating Neural Networks for Pattern Classification: Its Stability Properties and Some Test Results, Extending planning languages to include optimization capabilities, and End-user optimization with spreadsheet models.