Sciweavers

3717 search results - page 5 / 744
» The Persistence of Statistical Information
Sort
View
ICML
2009
IEEE
14 years 2 months ago
Using fast weights to improve persistent contrastive divergence
The most commonly used learning algorithm for restricted Boltzmann machines is contrastive divergence which starts a Markov chain at a data point and runs the chain for only a few...
Tijmen Tieleman, Geoffrey E. Hinton
COMPGEOM
2009
ACM
14 years 2 months ago
Persistent cohomology and circular coordinates
Nonlinear dimensionality reduction (NLDR) algorithms such as Isomap, LLE and Laplacian Eigenmaps address the problem of representing high-dimensional nonlinear data in terms of lo...
Vin de Silva, Mikael Vejdemo-Johansson
IFL
1997
Springer
136views Formal Methods» more  IFL 1997»
13 years 11 months ago
Fully Persistent Graphs - Which One To Choose?
Functional programs, by nature, operate on functional, or persistent, data structures. Therefore, persistent graphs are a prerequisite to express functional graph algorithms. In th...
Martin Erwig
VLDB
1994
ACM
148views Database» more  VLDB 1994»
13 years 11 months ago
Fast Incremental Indexing for Full-Text Information Retrieval
Full-text information retrieval systems have traditionally been designed for archival environments. They often provide little or no support for adding new documents to an existing...
Eric W. Brown, James P. Callan, W. Bruce Croft
CSFW
2002
IEEE
14 years 12 days ago
Information Flow Security in Dynamic Contexts
We study a security property for processes in dynamic contexts, i.e., contexts that can be reconfigured at runtime. The security property that we propose in this paper, named Per...
Riccardo Focardi, Sabina Rossi