Sciweavers

986 search results - page 56 / 198
» Zero-data Learning of New Tasks
Sort
View
JMLR
2010
106views more  JMLR 2010»
15 years 2 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
ICRA
2007
IEEE
155views Robotics» more  ICRA 2007»
16 years 1 months ago
Dogged Learning for Robots
— Ubiquitous robots need the ability to adapt their behaviour to the changing situations and demands they will encounter during their lifetimes. In particular, non-technical user...
Daniel H. Grollman, Odest Chadwicke Jenkins
MA
1999
Springer
87views Communications» more  MA 1999»
15 years 11 months ago
Communicating Neural Network Knowledge between Agents in a Simulated Aerial Reconnaissance System
In order to maintain their performance in a dynamic environment, agents may be required to modify their learning behavior during run-time. If an agent utilizes a rule-based system...
Stephen Quirolgico, K. Canfield, Timothy W. Finin,...
ICML
2010
IEEE
15 years 8 months ago
Improved Local Coordinate Coding using Local Tangents
Local Coordinate Coding (LCC), introduced in (Yu et al., 2009), is a high dimensional nonlinear learning method that explicitly takes advantage of the geometric structure of the d...
Kai Yu, Tong Zhang
SIGDIAL
2010
15 years 5 months ago
Adaptive Referring Expression Generation in Spoken Dialogue Systems: Evaluation with Real Users
We present new results from a real-user evaluation of a data-driven approach to learning user-adaptive referring expression generation (REG) policies for spoken dialogue systems. ...
Srinivasan Janarthanam, Oliver Lemon