In many learning problems prior knowledge about pattern variations can be formalized and beneficially incorporated into the analysis system. The corresponding notion of invarianc...
Increasing scale, dynamism, and complexity of hybrid grids make traditional grid resource scheduling approaches difficult. In such grids, where resource volatility and dynamism is...
Reinforcement Learning is commonly used for learning tasks in robotics, however, traditional algorithms can take very long training times. Reward shaping has been recently used to ...
Ana C. Tenorio-Gonzalez, Eduardo F. Morales, Luis ...
Reduction is a common component of many applications, but can often be the limiting factor for parallelization. Previous reduction work has focused on detecting reduction idioms a...
Abstract Image alignment has been a long standing problem in computer vision. Parameterized Appearance Models (PAMs) such as the Lucas-Kanade method, Eigentracking, and Active Appe...