Sciweavers

2455 search results - page 234 / 491
» Learning Composite Concepts
Sort
View
EACL
2006
ACL Anthology
15 years 7 months ago
Using Reinforcement Learning to Build a Better Model of Dialogue State
Given the growing complexity of tasks that spoken dialogue systems are trying to handle, Reinforcement Learning (RL) has been increasingly used as a way of automatically learning ...
Joel R. Tetreault, Diane J. Litman
AAAI
1997
15 years 7 months ago
Worst-Case Absolute Loss Bounds for Linear Learning Algorithms
The absolute loss is the absolute difference between the desired and predicted outcome. I demonstrateworst-case upper bounds on the absolute loss for the perceptron algorithm and ...
Tom Bylander
IJCAI
1989
15 years 7 months ago
Learning Novel Domains Through Curiosity and Conjecture
This paper describes DIDO, a system we have developed to carry out exploratory learning of unfamiliar domains without assistance from an external teacher. The program incorporates...
Paul D. Scott, Shaul Markovitch
ICIP
2010
IEEE
15 years 4 months ago
Face-TLD: Tracking-Learning-Detection applied to faces
A novel system for long-term tracking of a human face in unconstrained videos is built on Tracking-Learning-Detection (TLD) approach. The system extends TLD with the concept of a ...
Zdenek Kalal, Krystian Mikolajczyk, Jiri Matas
NAACL
2010
15 years 4 months ago
Engaging learning groups using Social Interaction Strategies
Conversational Agents have been shown to be effective tutors in a wide range of educational domains. However, these agents are often ignored and abused in collaborative learning s...
Rohit Kumar, Carolyn Penstein Rosé