Sciweavers

2623 search results - page 262 / 525
» Universal Learning Theory
Sort
View
ECAI
2004
Springer
16 years 5 min ago
A Backtracking Strategy for Order-Independent Incremental Learning
Agents that exist in an environment that changes over time, and are able to take into account the temporal nature of experience, are commonly called incremental learners. It is wid...
Nicola Di Mauro, Floriana Esposito, Stefano Ferill...
DEXAW
2002
IEEE
91views Database» more  DEXAW 2002»
15 years 11 months ago
Using Digital Narratives to Support the Collaborative Learning and Exploration of Cultural Heritage
Cultural institutions increasingly see the need to play an important role in the lifelong learning of citizens. Recent trends, particularly in science museums, have been toward su...
Paul Mulholland, Trevor D. Collins
ECML
1998
Springer
15 years 10 months ago
Predicate Invention and Learning from Positive Examples Only
Previous bias shift approaches to predicate invention are not applicable to learning from positive examples only, if a complete hypothesis can be found in the given language, as ne...
Henrik Boström
TNN
1998
111views more  TNN 1998»
15 years 6 months ago
Asymptotic distributions associated to Oja's learning equation for neural networks
— In this paper, we perform a complete asymptotic performance analysis of the stochastic approximation algorithm (denoted subspace network learning algorithm) derived from Oja’...
Jean Pierre Delmas, Jean-Francois Cardos
TKDE
2010
224views more  TKDE 2010»
15 years 5 months ago
Probabilistic Topic Models for Learning Terminological Ontologies
—Probabilistic topic models were originally developed and utilised for document modeling and topic extraction in Information Retrieval. In this paper we describe a new approach f...
Wang Wei, Payam M. Barnaghi, Andrzej Bargiela