Sciweavers

986 search results - page 56 / 198
» Zero-data Learning of New Tasks
Sort
View
129
Voted
JMLR
2010
106views more  JMLR 2010»
14 years 10 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, ...
116
Voted
ICRA
2007
IEEE
155views Robotics» more  ICRA 2007»
15 years 10 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
123
Voted
MA
1999
Springer
87views Communications» more  MA 1999»
15 years 8 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,...
120
Voted
ICML
2010
IEEE
15 years 4 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
159
Voted
SIGDIAL
2010
15 years 1 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