Sciweavers

4660 search results - page 397 / 932
» Learning from imperfect data
Sort
View
ICASSP
2008
IEEE
16 years 1 months ago
Improving Spoken Language Understanding with information retrieval and active learning methods
In the context of deployed spoken dialogue telecom services, we introduce a preprocessor called Fiction into the Spoken Language Understanding (SLU) component. It acts as an inter...
Isabelle Jars, Franck Panaget
ICRA
2007
IEEE
147views Robotics» more  ICRA 2007»
16 years 1 months ago
Neural Reinforcement Learning Controllers for a Real Robot Application
— Accurate and fast control of wheel speeds in the presence of noise and nonlinearities is one of the crucial requirements for building fast mobile robots, as they are required i...
Roland Hafner, Martin Riedmiller
ECAI
2004
Springer
16 years 7 days ago
Active Learning for Robot Manipulation
Abstract— Learning techniques in robotic grasping applications have usually been concerned with the way a hand approaches to an object, or with improving the motor control of man...
Antonio Morales, Eris Chinellato, Andrew H. Fagg, ...
AI
1998
Springer
15 years 11 months ago
Sequential Instance-Based Learning
This paper presents and evaluates sequential instance-based learning (SIBL), an approach to action selection based upon data gleaned from prior problem solving experiences. SIBL le...
Susan L. Epstein, Jenngang Shih
IICAI
2003
15 years 8 months ago
Performance Analysis of an Acyclic Genetic approach to Learn Bayesian Network Structure
Abstract. We introduce a new genetic algorithm approach for learning a Bayesian network structure from data. Our method is capable of learning over all node orderings and structure...
Pankaj B. Gupta, Vicki H. Allan