This paper describes how we have extended a module structure of the Smalltalk LearningWorks to provide a programming environment deigned for very large scale technology transfer. ...
Mark Woodman, Robert Griffiths, Malcolm Macgregor,...
We consider the problem of recognizing 3-D objects from 2-D images using geometric models and assuming different viewing angles and positions. Our goal is to recognize and localize...
When an image is viewed at varying resolutions, it is known to create discrete perceptual jumps or transitions amid the continuous intensity changes. In this paper, we study a per...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
We use unsupervised probabilistic machine learning ideas to try to explain the kinds of learning observed in real neurons, the goal being to connect abstract principles of self-or...