Sciweavers

148 search results - page 14 / 30
» icml 2010
Sort
View
ICML
2010
IEEE
13 years 11 months ago
Deep networks for robust visual recognition
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
Yichuan Tang, Chris Eliasmith
ICML
2010
IEEE
13 years 11 months ago
Sequential Projection Learning for Hashing with Compact Codes
Hashing based Approximate Nearest Neighbor (ANN) search has attracted much attention due to its fast query time and drastically reduced storage. However, most of the hashing metho...
Jun Wang, Sanjiv Kumar, Shih-Fu Chang
ICML
2010
IEEE
13 years 11 months ago
Learning Programs: A Hierarchical Bayesian Approach
We are interested in learning programs for multiple related tasks given only a few training examples per task. Since the program for a single task is underdetermined by its data, ...
Percy Liang, Michael I. Jordan, Dan Klein
ICML
2010
IEEE
13 years 11 months ago
A Conditional Random Field for Multiple-Instance Learning
We present MI-CRF, a conditional random field (CRF) model for multiple instance learning (MIL). MI-CRF models bags as nodes in a CRF with instances as their states. It combines di...
Thomas Deselaers, Vittorio Ferrari
ICML
2010
IEEE
13 years 11 months ago
Supervised Aggregation of Classifiers using Artificial Prediction Markets
Prediction markets are used in real life to predict outcomes of interest such as presidential elections. In this work we introduce a mathematical theory for Artificial Prediction ...
Nathan Lay, Adrian Barbu