Sciweavers

1351 search results - page 252 / 271
» Learning from compressed observations
Sort
View
NIPS
1996
13 years 11 months ago
A Model of Recurrent Interactions in Primary Visual Cortex
A general feature of the cerebral cortex is its massive interconnectivity-ithas been estimatedanatomically 15 that cortical neurons receive on the order of 10,000 synapses, the ma...
Emanuel Todorov, Athanassios Siapas, David Somers
CVPR
2006
IEEE
14 years 11 months ago
Escaping local minima through hierarchical model selection: Automatic object discovery, segmentation, and tracking in video
Recently, the generative modeling approach to video segmentation has been gaining popularity in the computer vision community. For example, the flexible sprites framework has been...
Nebojsa Jojic, John M. Winn, Larry Zitnick
ECCV
2004
Springer
14 years 11 months ago
A Boosted Particle Filter: Multitarget Detection and Tracking
The problem of tracking a varying number of non-rigid objects has two major difficulties. First, the observation models and target distributions can be highly non-linear and non-Ga...
Kenji Okuma, Ali Taleghani, Nando de Freitas, Jame...
KDD
2004
ACM
154views Data Mining» more  KDD 2004»
14 years 10 months ago
Diagnosing extrapolation: tree-based density estimation
There has historically been very little concern with extrapolation in Machine Learning, yet extrapolation can be critical to diagnose. Predictor functions are almost always learne...
Giles Hooker
KDD
2004
ACM
166views Data Mining» more  KDD 2004»
14 years 10 months ago
Predicting prostate cancer recurrence via maximizing the concordance index
In order to effectively use machine learning algorithms, e.g., neural networks, for the analysis of survival data, the correct treatment of censored data is crucial. The concordan...
Lian Yan, David Verbel, Olivier Saidi