Sciweavers

Share
ICML
2009
IEEE
10 years 8 months ago
Deep learning from temporal coherence in video
This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled v...
Hossein Mobahi, Ronan Collobert, Jason Weston
ICML
2009
IEEE
10 years 8 months ago
Trajectory prediction: learning to map situations to robot trajectories
Trajectory planning and optimization is a fundamental problem in articulated robotics. Algorithms used typically for this problem compute optimal trajectories from scratch in a ne...
Nikolay Jetchev, Marc Toussaint
ICML
2009
IEEE
10 years 8 months ago
Online feature elicitation in interactive optimization
Most models of utility elicitation in decision support and interactive optimization assume a predefined set of "catalog" features over which user preferences are express...
Craig Boutilier, Kevin Regan, Paolo Viappiani
ICML
2009
IEEE
10 years 8 months ago
Domain adaptation from multiple sources via auxiliary classifiers
We propose a multiple source domain adaptation method, referred to as Domain Adaptation Machine (DAM), to learn a robust decision function (referred to as target classifier) for l...
Lixin Duan, Ivor W. Tsang, Dong Xu, Tat-Seng Chua
ICML
2009
IEEE
10 years 8 months ago
Robust bounds for classification via selective sampling
We introduce a new algorithm for binary classification in the selective sampling protocol. Our algorithm uses Regularized Least Squares (RLS) as base classifier, and for this reas...
Nicolò Cesa-Bianchi, Claudio Gentile, Franc...
ICML
2009
IEEE
10 years 8 months ago
Learning from measurements in exponential families
Given a model family and a set of unlabeled examples, one could either label specific examples or state general constraints--both provide information about the desired model. In g...
Percy Liang, Michael I. Jordan, Dan Klein
ICML
2009
IEEE
10 years 8 months ago
Fitting a graph to vector data
Samuel I. Daitch, Jonathan A. Kelner, Daniel A. Sp...
ICML
2009
IEEE
10 years 8 months ago
Multi-instance learning by treating instances as non-I.I.D. samples
Previous studies on multi-instance learning typically treated instances in the bags as independently and identically distributed. The instances in a bag, however, are rarely indep...
Zhi-Hua Zhou, Yu-Yin Sun, Yu-Feng Li
ICML
2009
IEEE
10 years 8 months ago
Learning Markov logic network structure via hypergraph lifting
Markov logic networks (MLNs) combine logic and probability by attaching weights to first-order clauses, and viewing these as templates for features of Markov networks. Learning ML...
Stanley Kok, Pedro Domingos
ICML
2009
IEEE
10 years 8 months ago
Hilbert space embeddings of conditional distributions with applications to dynamical systems
In this paper, we extend the Hilbert space embedding approach to handle conditional distributions. We derive a kernel estimate for the conditional embedding, and show its connecti...
Le Song, Jonathan Huang, Alexander J. Smola, Kenji...
books