We present a new approach for dealing with distribution change and concept drift when learning from data sequences that may vary with time. We use sliding windows whose size, inst...
— We aim to perform robust and fast vision-based localization using a pre-existing large map of the scene. A key step in localization is associating the features extracted from t...
In e-learning initiatives content creators are usually required to arrange a set of learning resources in order to present them in a comprehensive way to the learner. Course mater...
The robot described in this paper learns words that relate to objects and their attributes and also learns concepts, which may be recursive, that involve relationships between sev...
Abstract. We investigate the problem of using function approximation in reinforcement learning where the agent’s policy is represented as a classifier mapping states to actions....