Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...
Exploration/Exploitation equilibrium is one of the most challenging issues in reinforcement learning area as well as learning classifier systems such as XCS. In this paper1 , an i...
We extend the well-known BFGS quasi-Newton method and its memory-limited variant LBFGS to the optimization of nonsmooth convex objectives. This is done in a rigorous fashion by ge...
Kernel methods yield state-of-the-art performance in certain applications such as image classification and object detection. However, large scale problems require machine learning...
Sreekanth Vempati, Andrea Vedaldi, Andrew Zisserma...