A control of real processes requires different approach to neural network learning. The presented modification of backpropagation learning algorithm changes a meaning of learning...
Predictive state representations (PSRs) are a recently proposed way of modeling controlled dynamical systems. PSR-based models use predictions of observable outcomes of tests that...
This paper describes a dynamic computer-based business learning environment and the results from applying it in a real-world business organization. We argue for using learning too...
Automatic detection of dynamic events in video sequences has a variety of applications including visual surveillance and monitoring, video highlight extraction, intelligent transp...