Sciweavers

966 search results - page 11 / 194
» A Two-Level Learning Method for Generalized Multi-instance P...
Sort
View
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
15 years 3 months ago
Co-evolving recurrent neurons learn deep memory POMDPs
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...
Faustino J. Gomez, Jürgen Schmidhuber
GECCO
2006
Springer
208views Optimization» more  GECCO 2006»
15 years 1 months ago
Comparing evolutionary and temporal difference methods in a reinforcement learning domain
Both genetic algorithms (GAs) and temporal difference (TD) methods have proven effective at solving reinforcement learning (RL) problems. However, since few rigorous empirical com...
Matthew E. Taylor, Shimon Whiteson, Peter Stone
GECCO
2005
Springer
15 years 3 months ago
Intelligent exploration method for XCS
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...
Ali Hamzeh, Adel Rahmani
JMLR
2010
143views more  JMLR 2010»
14 years 8 months ago
A Quasi-Newton Approach to Nonsmooth Convex Optimization Problems in Machine Learning
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...
Jin Yu, S. V. N. Vishwanathan, Simon Günter, ...
BMVC
2010
14 years 7 months ago
Generalized RBF feature maps for Efficient Detection
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...