86 search results - page 15 / 18 » jmlr 2012 |
JMLR
2012
13 years 13 days ago
2012
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
115
click to vote
JMLR
2012
13 years 12 days ago
2012
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...
107
click to vote
JMLR
2012
13 years 12 days ago
2012
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample d...
108
click to vote
JMLR
2012
13 years 12 days ago
2012
Open-text semantic parsers are designed to interpret any statement in natural language by inferring a corresponding meaning representation (MR – a formal representation of its s...
100
click to vote
JMLR
2012
13 years 12 days ago
2012
We propose a new family of latent variable models called max-margin min-entropy (m3e) models, which define a distribution over the output and the hidden variables conditioned on ...