Recent psychological and neurological evidence suggests that biological object recognition is a process of matching sensed images to stored iconic memories. This paper presents a p...
Estimating the error rates of classifiers or regression models is a fundamental task in machine learning which has thus far been studied exclusively using supervised learning tech...
Pinar Donmez, Guy Lebanon, Krishnakumar Balasubram...
In this paper we present a framework for using multi-layer perceptron (MLP) networks in nonlinear generative models trained by variational Bayesian learning. The nonlinearity is h...
Information distillation techniques are used to analyze and interpret large volumes of speech and text archives in multiple languages and produce structured information of interes...
We present a coreference resolver called BABAR that uses contextual role knowledge to evaluate possible antecedents for an anaphor. BABAR uses information extraction patterns to i...