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...
: This paper describes a Conceptual Framework underpinning "Systems that Care" in terms of educational systems that take account of motivation, metacognition and affect, ...
Benedict du Boulay, Katerina Avramides, Rosemary L...
A wide variety of machine learning problems can be described as minimizing a regularized risk functional, with different algorithms using different notions of risk and different r...
Choon Hui Teo, Alex J. Smola, S. V. N. Vishwanatha...
This paper presents a model of neural network embodiment of intentions and planning mechanisms for autonomous agents. The model bridges the dichotomy of symbolic and non-symbolic ...