23 search results - page 2 / 5 » Unifying generative and discriminative learning principles |
C5
2004
IEEE
13 years 8 months ago
2004
IEEE
Existing online learning experiences lack the social dimension that characterizes learning in the real world. This social dimension extends beyond the traditional classroom into t...
ICCV
2005
IEEE
14 years 6 months ago
2005
IEEE
Learning models for detecting and classifying object categories is a challenging problem in machine vision. While discriminative approaches to learning and classification have, in...
JMLR
2010
12 years 11 months ago
2010
We present a new estimation principle for parameterized statistical models. The idea is to perform nonlinear logistic regression to discriminate between the observed data and some...
SIGIR
2010
ACM
13 years 8 months ago
2010
ACM
Generative models such as statistical language modeling have been widely studied in the task of expert search to model the relationship between experts and their expertise indicat...
ICML
2008
IEEE
14 years 5 months ago
2008
IEEE
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...