The performance of image retrieval with SVM active learning is known to be poor when started with few labelled images only. In this paper, the problem is solved by incorporating t...
We consider the problem of automatically learning color enhancements from a small set of sample color pairs, and describing the enhancement by a three-dimensional look-uptable tha...
Abstract. This paper presents a methodology for automatically customizing a scenario to suit a learner’s abilities, needs, or goals. Training scenarios are often utilized to give...
Reinforcement learning techniques are increasingly being used to solve di cult problems in control and combinatorial optimization with promising results. Implicit imitation can acc...
This paper presents and evaluates sequential instance-based learning (SIBL), an approach to action selection based upon data gleaned from prior problem solving experiences. SIBL le...