— Most research in machine learning focuses on scenarios in which a learner faces a single learning task, independently of other learning tasks or prior knowledge. In reality, ho...
We empirically evaluate several state-of-theart methods for constructing ensembles of heterogeneous classifiers with stacking and show that they perform (at best) comparably to se...
In this paper we present a new approach to enabling pedagogically sound reuse and re-purposing of online learning objects in a community of practice. The lack of specific software...
Chu Wang, Hugh C. Davis, Kate Dickens, Gary Wills,...
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
— Handling catastrophic forgetting is an interesting and challenging topic in modeling the memory mechanisms of the human brain using machine learning models. From a more general...