Collaborative Research: Globally Optimal Neural Computing: Algorithms and Applications

University Of Illinois At Urbana-Champaign, Urbana IL

Investigators

Abstract

0098770 Sahinidis This grant supports a collaboration between a member of the global optimization community (Nick Sahinidis) and an expert in neural computation and optimization (Theodore Trafalis) to develop novel neural network training algorithms and demonstrate their benefits in solving large-scale learning) problems. The application of neural networks to all aspects of technology has escalated recently as engineers and scientists have widely embraced neural computing in their quest for deeper understanding of complex phenomena and systems. Finding the best possible neural network for a particular application requires choosing the network parameters in a way that minimizes learning errors. Even for simple learning problems, the error function possesses a large number of local minima (isolated valleys). Despite the enormous amount of attention devoted to neural networks, there is currently no efficient method that can identify with certainty time global minimum of the error function. Current approaches, such as back-propagation and stochastic search methods, may get trapped at local minima corresponding to large learning errors and suboptimal neural networks. This may lead to incorrect inferences and devastate decision makers. Globally optimal neural computing holds the promise of an enabling technology that could significantly improve learning in many diverse application domains. The results of the proposed research will be implemented in the their widely distributed global optimization software package and will be made available to the research community.