Sciweavers

986 search results - page 139 / 198
» Zero-data Learning of New Tasks
Sort
View
ICML
2005
IEEE
15 years 10 months ago
Bounded real-time dynamic programming: RTDP with monotone upper bounds and performance guarantees
MDPs are an attractive formalization for planning, but realistic problems often have intractably large state spaces. When we only need a partial policy to get from a fixed start s...
H. Brendan McMahan, Maxim Likhachev, Geoffrey J. G...
SAC
2006
ACM
15 years 3 months ago
Discretization from data streams: applications to histograms and data mining
Abstract. In this paper we propose a new method to perform incremental discretization. The basic idea is to perform the task in two layers. The first layer receives the sequence o...
João Gama, Carlos Pinto
ACOM
2004
Springer
15 years 3 months ago
Optimal Communication Vocabularies and Heterogeneous Ontologies
In this paper, we will consider the alignment of heterogeneous ontologies in multi agent systems. We will start from the idea that each individual agent is specialized in solving ...
Jurriaan van Diggelen, Robbert-Jan Beun, Frank Dig...
AIRS
2004
Springer
15 years 3 months ago
A Bootstrapping Approach for Geographic Named Entity Annotation
Abstract. Geographic named entities can be classified into many subtypes that are useful for applications such as information extraction and question answering. In this paper, we ...
Seungwoo Lee, Gary Geunbae Lee
ICALT
2003
IEEE
15 years 3 months ago
On Tools for Analysis of Collaborative Problem Solving
Analysis of collaborative problem solving involves analysis of dialogue and interaction, analysis of tasks and social roles through ethnographic and other field studies. Use of to...
Nikolaos M. Avouris, Vassilis Komis, Georgios Fiot...