We present the use of layered probabilistic representations for modeling human activities, and describe how we use the representation to do sensing, learning, and inference at mul...
This paper describes a computationally feasible approximation to the AIXI agent, a universal reinforcement learning agent for arbitrary environments. AIXI is scaled down in two ke...
Joel Veness, Kee Siong Ng, Marcus Hutter, William ...
Identifying suitable image features is a central challenge in computer vision, ranging from representations for lowlevel to high-level vision. Due to the difficulty of this task,...
The input to an algorithm that learns a binary classifier normally consists of two sets of examples, where one set consists of positive examples of the concept to be learned, and ...
This paper presents a framework for a learning based approach to dynamically evolve the conceptual structure of a database in order to facilitate virtual representation of data in ...