We show how the regularizer of Transductive Support Vector Machines (TSVM) can be trained by stochastic gradient descent for linear models and multi-layer architectures. The resul...
Michael Karlen, Jason Weston, Ayse Erkan, Ronan Co...
We present four new reinforcement learning algorithms based on actor-critic and natural-gradient ideas, and provide their convergence proofs. Actor-critic reinforcement learning m...
Shalabh Bhatnagar, Richard S. Sutton, Mohammad Gha...
Boosting has been widely applied in computer vision, especially after Viola and Jones's seminal work [23]. The marriage of rectangular features and integral-imageenabled fast...
In the standard feature selection problem, we are given a fixed set of candidate features for use in a learning problem, and must select a subset that will be used to train a mode...
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...