In this work we show that verbs reliably represent texts when machine learning algorithms are used to learn opinions. We identify semantic verb categories that capture essential pr...
Learning to predict rare events from sequences of events with categorical features is an important, real-world, problem that existing statistical and machine learning methods are ...
We consider the task of learning mappings from sequential data to real-valued responses. We present and evaluate an approach to learning a type of hidden Markov model (HMM) for re...
We present an expressive agent design language for reinforcement learning that allows the user to constrain the policies considered by the learning process.The language includes s...
Detecting shadows from images can significantly improve the performance of several vision tasks such as object detection and tracking. Recent approaches have mainly used illuminat...