Sciweavers

799 search results - page 52 / 160
» Heterogeneous reasoning in learning to model
Sort
View
ICML
2004
IEEE
15 years 10 months ago
Learning random walk models for inducing word dependency distributions
Many NLP tasks rely on accurately estimating word dependency probabilities P(w1|w2), where the words w1 and w2 have a particular relationship (such as verb-object). Because of the...
Kristina Toutanova, Christopher D. Manning, Andrew...
SEMWEB
2010
Springer
14 years 7 months ago
Semantic Techniques for Enabling Knowledge Reuse in Conceptual Modelling
Abstract. Conceptual modelling tools allow users to construct formal representations of their conceptualisations. These models are typically developed in isolation, unrelated to ot...
Jorge Gracia del Río, Jochem Liem, Esther L...
ILP
2007
Springer
15 years 3 months ago
Building Relational World Models for Reinforcement Learning
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
Trevor Walker, Lisa Torrey, Jude W. Shavlik, Richa...
ENTCS
2007
119views more  ENTCS 2007»
14 years 9 months ago
Interpolant Learning and Reuse in SAT-Based Model Checking
Bounded Model Checking (BMC) is one of the most paradigmatic practical applications of Boolean Satisfiability (SAT). The utilization of SAT in model checking has allowed signifi...
João Marques-Silva
AAAI
2007
15 years 2 days ago
Detecting Execution Failures Using Learned Action Models
reason with abstracted models of the behaviours they use to construct plans. When plans are turned into the instructions that drive an executive, the real behaviours interacting w...
Maria Fox, Jonathan Gough, Derek Long