ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
We present a reinforcement learning architecture, Dyna-2, that encompasses both samplebased learning and sample-based search, and that generalises across states during both learni...
ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
Graph transduction methods label input data by learning a classification function that is regularized to exhibit smoothness along a graph over labeled and unlabeled samples. In pr...
ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
We present an algorithm for on-line, incremental discovery of temporal-difference (TD) networks. The key contribution is the establishment of three criteria to expand a node in TD...
ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
In the absence of explicit queries, an alternative is to try to infer users' interests from implicit feedback signals, such as clickstreams or eye tracking. The interests, fo...
ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
We consider the problem of optimizing multilabel MRFs, which is in general NP-hard and ubiquitous in low-level computer vision. One approach for its solution is to formulate it as...
ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
We introduce confidence-weighted linear classifiers, which add parameter confidence information to linear classifiers. Online learners in this setting update both classifier param...
ICML
2008
IEEE
15 years 10 days ago
2008
IEEE
Most existing sparse Gaussian process (g.p.) models seek computational advantages by basing their computations on a set of m basis functions that are the covariance function of th...
ICML
2008
IEEE
2008
IEEE
A unified architecture for natural language processing: deep neural networks with multitask learning
15 years 10 days ago
We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity...