A novel method to improve the generalization performance of the Minimum Classification Error (MCE) / Generalized Probabilistic Descent (GPD) learning is proposed. The MCE/GPD learn...
One of the most important problems for an intelligent tutoring system is deciding how to respond when a student asks for help. Responding cooperatively requires an understanding o...
A PDM (Pulse Density Modulating) digital neural network system, which consists of 1,000 neurons physically interconnected by one million 7-bit synapses, was developed in our labor...
In this paper we address the problem of discretization in the context of learning Bayesian networks (BNs) from data containing both continuous and discrete variables. We describe ...
The evolution of language implies the parallel evolution of an ability to respond appropriately to signals (language understanding) and an ability to produce the appropriate signa...