— 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...
In this paper we analyze the PAC learning abilities of several simple iterative algorithms for learning linear threshold functions, obtaining both positive and negative results. W...
In this paper we examine some problems related to capturing the structure and the topic name space of learning content in the context of Topic Map authoring. We demonstrate that t...
Systems that learn from examples often express the learned concept in the form of a disjunctive description. Disjuncts that correctly classify few training examples are known as s...
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...