We consider reinforcement learning in systems with unknown dynamics. Algorithms such as E3 (Kearns and Singh, 2002) learn near-optimal policies by using "exploration policies...
Hierarchical models of motor function are described in which the motor system encodes a hierarchy of dynamical motor primitives. The models are based on continuous attractor neura...
We propose dynamical systems trees (DSTs) as a flexible model for describing multiple processes that interact via a hierarchy of aggregating processes. DSTs extend nonlinear dynam...
This article presents an empirical study performed to evaluate the Moodle usability, from the point of view of teachers who are using this system to support their classes. The usa...
This paper defines a type of constrained artificial neural network (ANN) that enables analytical certification arguments whilst retaining valuable performance characteristics. ...