On May 14th 2012, at Dipartimento di Elettronica e Informazione of Politecnico di Milano, professor Jun Wang from Chinese University of Hong Kong will give a distinguished lecture entitled “The State of the Art of Multiple-winners-take-all Networks: Neurodynamics formulation, Models, and Applications”.
This event is organized by IEEE Computational Intelligence Society Italian Chapter. Here’s the complete announcement:
IEEE CIS Distinguished Lecturer Program
Politecnico di Milano
Dipartimento di Elettronica e Informazione
Sala Seminari 14/05/2012 at 10h00
Piazza L. da Vinci 32, 20133 Milano, Italy
The State of the Art of Multiple-winners-take-all Networks:
Neurodynamics formulation, Models, and Applications
Department of Mechanical & Automation Engineering
Chinese University of Hong Kong
Winner-take-all is a general rule commonly used in many applications such as machine learning and data mining. K-winners-
take-all is a generalization of winner-take-all with multiple winners. Over the last twenty years, many K-winners-take-all neural networks and circuits have been developed with varied complexity and performance. In this talk, I will start with several mathematical problem formulations of the K-winners-take-all solutions via neurodynamic optimization, then present several K winners-take-all networks with reducing model complexity based on our neurodynamic optimization models. Finally, we will
introduce the best one with the simplest model complexity and maximum computational efficiency. Analytical and Monte Carlo simulation results will be shown to demonstrate the computing characteristics and performance. The applications to parallel sorting, rank-order filtering, and information retrieval will be also discussed.