Sciweavers

1252 search results - page 157 / 251
» Knowledge Representation Issues in Control Knowledge Learnin...
Sort
View
DLOG
2011
14 years 1 months ago
On the Problem of Weighted Max-DL-SAT and its Application to Image Labeling
Abstract. For a number of problems, such as ontology learning or image labeling, we need to handle uncertainty and inconsistencies in an appropriate way. Fuzzy and Probabilistic De...
Stefan Scheglmann, Carsten Saathoff, Steffen Staab
CORR
2010
Springer
193views Education» more  CORR 2010»
14 years 8 months ago
A Probabilistic Approach for Learning Folksonomies from Structured Data
Learning structured representations has emerged as an important problem in many domains, including document and Web data mining, bioinformatics, and image analysis. One approach t...
Anon Plangprasopchok, Kristina Lerman, Lise Getoor
NIPS
2007
14 years 11 months ago
Learning and using relational theories
Much of human knowledge is organized into sophisticated systems that are often called intuitive theories. We propose that intuitive theories are mentally represented in a logical ...
Charles Kemp, Noah Goodman, Joshua B. Tenenbaum
KDD
1997
ACM
169views Data Mining» more  KDD 1997»
15 years 1 months ago
Learning to Extract Text-Based Information from the World Wide Web
Thereis a wealthof informationto be minedfromnarrative text on the WorldWideWeb.Unfortunately, standard natural language processing (NLP)extraction techniques expect full, grammat...
Stephen Soderland
FLAIRS
2007
15 years 4 days ago
Context-Sensitive MTL Networks for Machine Lifelong Learning
Context-sensitive Multiple Task Learning, or csMTL, is presented as a method of inductive transfer that uses a single output neural network and additional contextual inputs for le...
Daniel L. Silver, Ryan Poirier