In this work we take a novel view of nonlinear manifold learning. Usually, manifold learning is formulated in terms of finding an embedding or `unrolling' of a manifold into ...
A widely acknowledged drawback of many statistical modelling techniques, commonly used in machine learning, is that the resulting model is extremely difficult to interpret. A numb...
If robotic agents are to act autonomously they must have the ability to construct and reason about models of their physical environment. For example, planning to achieve goals req...
This paper presents a novel model of reinforcement learning agents. A feature of our learning agent model is to integrate analytic hierarchy process (AHP) into a standard reinforc...
While argumentation is highly important for humans in many different aspects of life, it is hard to teach large groups to argue. Classic face-to-face approaches, which have shown ...