Sciweavers

ICML
2006
IEEE
15 years 8 days ago
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...
Alex Graves, Faustino J. Gomez, Jürgen Schmid...
ICML
2006
IEEE
15 years 8 days ago
A choice model with infinitely many latent features
Elimination by aspects (EBA) is a probabilistic choice model describing how humans decide between several options. The options from which the choice is made are characterized by b...
Carl Edward Rasmussen, Dilan Görür, Fran...
ICML
2006
IEEE
15 years 8 days ago
Nightmare at test time: robust learning by feature deletion
When constructing a classifier from labeled data, it is important not to assign too much weight to any single input feature, in order to increase the robustness of the classifier....
Amir Globerson, Sam T. Roweis
ICML
2006
IEEE
15 years 8 days ago
Kernelizing the output of tree-based methods
We extend tree-based methods to the prediction of structured outputs using a kernelization of the algorithm that allows one to grow trees as soon as a kernel can be defined on the...
Florence d'Alché-Buc, Louis Wehenkel, Pierr...
ICML
2006
IEEE
15 years 8 days ago
The rate adapting poisson model for information retrieval and object recognition
Probabilistic modelling of text data in the bagof-words representation has been dominated by directed graphical models such as pLSI, LDA, NMF, and discrete PCA. Recently, state of...
Peter V. Gehler, Alex Holub, Max Welling
ICML
2006
IEEE
15 years 8 days ago
Regression with the optimised combination technique
We consider the sparse grid combination technique for regression, which we regard as a problem of function reconstruction in some given function space. We use a regularised least ...
Jochen Garcke
ICML
2006
IEEE
15 years 8 days ago
Online multiclass learning by interclass hypothesis sharing
We describe a general framework for online multiclass learning based on the notion of hypothesis sharing. In our framework sets of classes are associated with hypotheses. Thus, al...
Michael Fink 0002, Shai Shalev-Shwartz, Yoram Sing...
ICML
2006
IEEE
15 years 8 days ago
Qualitative reinforcement learning
When the transition probabilities and rewards of a Markov Decision Process are specified exactly, the problem can be solved without any interaction with the environment. When no s...
Arkady Epshteyn, Gerald DeJong
ICML
2006
IEEE
15 years 8 days ago
A graphical model for predicting protein molecular function
We present a simple statistical model of molecular function evolution to predict protein function. The model description encodes general knowledge of how molecular function evolve...
Barbara E. Engelhardt, Michael I. Jordan, Steven E...
ICML
2006
IEEE
15 years 8 days ago
Clustering documents with an exponential-family approximation of the Dirichlet compound multinomial distribution
The Dirichlet compound multinomial (DCM) distribution, also called the multivariate Polya distribution, is a model for text documents that takes into account burstiness: the fact ...
Charles Elkan