A programming language that lacks facilities for concurrent programming can gain those facilities in two ways: the language can be extended with additional constructs, which will ...
The generalization of policies in reinforcement learning is a main issue, both from the theoretical model point of view and for their applicability. However, generalizing from a se...
Bag-of-words approaches to information retrieval (IR) are effective but assume independence between words. The Hyperspace Analogue to Language (HAL) is a cognitively motivated and...
We propose a unified data modeling approach that is equally applicable to supervised regression and classification applications, as well as to unsupervised probability density func...
We present new results on the well-studied problem of learning DNF expressions. We prove that an algorithm due to Kushilevitz and Mansour [13] can be used to weakly learn DNF form...
Avrim Blum, Merrick L. Furst, Jeffrey C. Jackson, ...