We propose a formal real-time semantics for UML statecharts aimed at the requirements level. A requirements-level model assumes perfect technology and has a considerably simpler se...
Despite all the progress in neural networks the technology is still brittle and sometimes difficult to apply. Automatic construction of networks and proper initialization of their...
In this paper, we study the use of support vector machine in text categorization. Unlike other machine learning techniques, it allows easy incorporation of new documents into an e...
Previous works on range image segmentation concentrate on surface patches that can be well represented by certain mathematical functions. In this paper we consider the more qualit...
Competitive learning is a technique for training classification and clustering networks. We have designed and fabricated an 11transistor primitive, that we term an automaximizing ...