Sciweavers

18 search results - page 2 / 4
» Using Physical Demonstrations, Background Knowledge and Voca...
Sort
View
TASLP
2008
149views more  TASLP 2008»
13 years 4 months ago
Using Articulatory Representations to Detect Segmental Errors in Nonnative Pronunciation
Abstract--Motivated by potential applications in second-language pedagogy, we present a novel approach to using articulatory information to improve automatic detection of typical p...
Joseph Tepperman, Shrikanth Narayanan
ACCV
2010
Springer
12 years 12 months ago
Unsupervised Selective Transfer Learning for Object Recognition
Abstract. We propose a novel unsupervised transfer learning framework that utilises unlabelled auxiliary data to quantify and select the most relevant transferrable knowledge for r...
Wei-Shi Zheng, Shaogang Gong, Tao Xiang
ATAL
2009
Springer
13 years 11 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 ...
PSYCHNOLOGY
2008
97views more  PSYCHNOLOGY 2008»
13 years 4 months ago
Being Inside the Quantum Atom
This article explores the possibility of using dynamic Educational Virtual Environments (EVEs) for helping students with limited background in physics and mathematics to deeply un...
Assimina M. Kontogeorgiou, Joan Bellou, Tassos A. ...
IROS
2008
IEEE
144views Robotics» more  IROS 2008»
13 years 11 months ago
Learning nonparametric policies by imitation
— A long cherished goal in artificial intelligence has been the ability to endow a robot with the capacity to learn and generalize skills from watching a human teacher. Such an ...
David B. Grimes, Rajesh P. N. Rao