Sciweavers

243 search results - page 8 / 49
» Learning Abstraction Hierarchies for Problem Solving
Sort
View
MLDM
2007
Springer
14 years 2 months ago
Discovering Plausible Explanations of Carcinogenecity in Chemical Compounds
Abstract. The goal of predictive toxicology is the automatic construction of carcinogenecity models. Most common artificial intelligence techniques used to construct these models ...
Eva Armengol
NIPS
2004
13 years 10 months ago
Intrinsically Motivated Reinforcement Learning
Psychologists call behavior intrinsically motivated when it is engaged in for its own sake rather than as a step toward solving a specific problem of clear practical value. But wh...
Satinder P. Singh, Andrew G. Barto, Nuttapong Chen...
CAIP
2009
Springer
246views Image Analysis» more  CAIP 2009»
14 years 3 months ago
Human Age Estimation by Metric Learning for Regression Problems
Abstract. The estimation of human age from face images is an interesting problem in computer vision. We proposed a general distance metric learning scheme for regression problems, ...
Yangjing Long
UM
2009
Springer
14 years 3 months ago
Context-Dependent Personalised Feedback Prioritisation in Exploratory Learning for Mathematical Generalisation
Abstract. In this paper we address the problem of prioritising feedback on the basis of multiple heterogeneous pieces of information in exploratory learning. The problem arises whe...
Mihaela Cocea, George D. Magoulas
PRICAI
2000
Springer
14 years 5 days ago
Generating Hierarchical Structure in Reinforcement Learning from State Variables
This paper presents the CQ algorithm which decomposes and solves a Markov Decision Process (MDP) by automatically generating a hierarchy of smaller MDPs using state variables. The ...
Bernhard Hengst