Sciweavers

275 search results - page 23 / 55
» Learning about and through Empirical Modelling
Sort
View
JMLR
2012
11 years 11 months ago
Structured Output Learning with High Order Loss Functions
Often when modeling structured domains, it is desirable to leverage information that is not naturally expressed as simply a label. Examples include knowledge about the evaluation ...
Daniel Tarlow, Richard S. Zemel
SIGIR
2000
ACM
14 years 24 days ago
Bridging the lexical chasm: statistical approaches to answer-finding
Abstract This paper investigates whether a machine can automatically learn the task of finding, within a large collection of candidate responses, the answers to questions. The lea...
Adam L. Berger, Rich Caruana, David Cohn, Dayne Fr...
JMLR
2010
106views more  JMLR 2010»
13 years 3 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
FGR
2004
IEEE
230views Biometrics» more  FGR 2004»
14 years 5 days ago
Tracking Humans using Prior and Learned Representations of Shape and Appearance
Tracking a moving person is challenging because a person's appearance in images changes significantly due to articulation, viewpoint changes, and lighting variation across a ...
Jongwoo Lim, David J. Kriegman
COGSR
2011
109views more  COGSR 2011»
13 years 3 months ago
How groups develop a specialized domain vocabulary: A cognitive multi-agent model
We simulate the evolution of a domain vocabulary in small communities. Empirical data show that human communicators can evolve graphical languages quickly in a constrained task (P...
David Reitter, Christian Lebiere