Abstract— Meta-Learning has been used to predict the performance of learning algorithms based on descriptive features of the learning problems. Each training example in this cont...
This article proposes an algorithm to automatically learn useful transformations of data to improve accuracy in supervised classification tasks. These transformations take the for...
We have proposed a complete system for text detection and localization in gray scale scene images. A boosting framework integrating feature and weak classifier selection based on...
An algorithm has been developed to automatically construct individual models of normal activity within a home using motion sensor data. Alerts can be generated when a period of in...
Paul Cuddihy, Jenny Weisenberg, Catherine Graichen...
Actor-Critic based approaches were among the first to address reinforcement learning in a general setting. Recently, these algorithms have gained renewed interest due to their gen...