Sciweavers

603 search results - page 11 / 121
» A theory of learning from different domains
Sort
View
ICRA
2009
IEEE
179views Robotics» more  ICRA 2009»
15 years 8 months ago
Automatic weight learning for multiple data sources when learning from demonstration
— Traditional approaches to programming robots are generally inaccessible to non-robotics-experts. A promising exception is the Learning from Demonstration paradigm. Here a polic...
Brenna Argall, Brett Browning, Manuela M. Veloso
AAAI
2006
15 years 2 months ago
Cross-Domain Knowledge Transfer Using Structured Representations
Previous work in knowledge transfer in machine learning has been restricted to tasks in a single domain. However, evidence from psychology and neuroscience suggests that humans ar...
Samarth Swarup, Sylvian R. Ray
IJCSA
2006
111views more  IJCSA 2006»
15 years 1 months ago
Using DocBook and XML Technologies to Create Adaptive Learning Content in Technical Domains
This work presents an XML-based authoring methodology that facilitates the different tasks associated with the development of standards-compliant e-learning content development. T...
Iván Martínez-Ortiz, Pablo Moreno-Ge...
ATAL
2009
Springer
15 years 8 months ago
MABLE: a framework for learning from natural instruction
The Modular Architecture for Bootstrapped Learning Experiments (MABLE) is a system that is being developed to allow humans to teach computers in the most natural manner possible: ...
Roger Mailler, Daniel Bryce, Jiaying Shen, Ciaran ...
EACL
2009
ACL Anthology
16 years 2 months ago
Improvements in Analogical Learning: Application to Translating Multi-Terms of the Medical Domain
Handling terminology is an important matter in a translation workflow. However, current Machine Translation (MT) systems do not yet propose anything proactive upon tools which ass...
François Yvon, Philippe Langlais, Pierre Zw...