Adaptive systems are widely encountered in many applications ranging through adaptive filtering and more generally adaptive signal processing, systems identific

On-line learning is one of the most commonly used techniques for training neural networks. Though it has been used successfully in many real-world applications,

The 31 papers collected here present original research results obtained in 1995-96, on Brownian motion and, more generally, diffusion processes, martingales, Wi

Reinforcement learning is a learning paradigm concerned with learning to control a system so as to maximize a numerical performance measure that expresses a lon