The effectiveness of knowledge transfer using classification algorithms depends on the difference between the distribution that generates the training examples and the one from wh...
s the Pus using the OpenCL API as the platform independent programming model. It has the proposal to extend OpenCL with a module that schedule and balance the workload over the CPU...
Abstract— This paper proposes a simulation-based active policy learning algorithm for finite-horizon, partially-observed sequential decision processes. The algorithm is tested i...
Ruben Martinez-Cantin, Nando de Freitas, Arnaud Do...
The launch of new features for mobile phones is increasing and the product life cycle symmetrically decreasing in duration as higher levels of sophistication are reached. Therefor...
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...