We describe a method for generating accurate, compact, human understandable text classifiers. Text datasets are indexed using Apache Lucene and Genetic Programs are used to constr...
FastICA is arguably one of the most widespread methods for independent component analysis. We focus on its deflation-based implementation, where the independent components are ext...
We consider the problem of constructing efficient locally decodable codes in the presence of a computationally bounded adversary. Assuming the existence of one-way functions, we c...
Abstract. We develop a probabilistic interpretation of non-linear component extraction in neural networks that activate their hidden units according to a softmaxlike mechanism. On ...
Abstract. Region-based memory management is a form of compiletime memory management, well-known from the functional programming world. This paper describes a static region analysis...