Sciweavers

Share
ICML
2008
IEEE
9 years 12 months ago
Sample-based learning and search with permanent and transient memories
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...
David Silver, Martin Müller 0003, Richard S. ...
ICML
2008
IEEE
9 years 12 months ago
Graph transduction via alternating minimization
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...
Jun Wang, Tony Jebara, Shih-Fu Chang
ICML
2008
IEEE
9 years 12 months ago
On-line discovery of temporal-difference networks
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...
Takaki Makino, Toshihisa Takagi
ICML
2008
IEEE
9 years 12 months ago
Learning to learn implicit queries from gaze patterns
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...
Antti Ajanki, Kai Puolamäki, Samuel Kaski
ICML
2008
IEEE
9 years 12 months ago
On partial optimality in multi-label MRFs
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...
Pushmeet Kohli, Alexander Shekhovtsov, Carsten Rot...
ICML
2008
IEEE
9 years 12 months ago
Confidence-weighted linear classification
We introduce confidence-weighted linear classifiers, which add parameter confidence information to linear classifiers. Online learners in this setting update both classifier param...
Mark Dredze, Koby Crammer, Fernando Pereira
ICML
2008
IEEE
9 years 12 months ago
Sparse multiscale gaussian process regression
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...
Bernhard Schölkopf, Christian Walder, Kwang I...
ICML
2008
IEEE
9 years 12 months ago
A unified architecture for natural language processing: deep neural networks with multitask learning
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...
Ronan Collobert, Jason Weston
books