Sciweavers

3256 search results - page 247 / 652
» Learning Linear Transformations
Sort
View
ICML
2006
IEEE
16 years 7 months ago
Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks
Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is...
Alex Graves, Faustino J. Gomez, Jürgen Schmid...
KI
2007
Springer
16 years 21 days ago
Training on the Job - Collecting Experience with Hierarchical Hybrid Automata
We propose a novel approach to experience collection for autonomous service robots performing complex activities. This approach enables robots to data for many learning problems at...
Alexandra Kirsch, Michael Beetz
ICRA
2005
IEEE
129views Robotics» more  ICRA 2005»
16 years 4 days ago
Fast Computational Methods for Visually Guided Robots
— This paper proposes numerical algorithms for reducing the computational cost of semi-supervised and active learning procedures for visually guided mobile robots from O(M3 ) to ...
Maryam Mahdaviani, Nando de Freitas, Bob Fraser, F...
AIPS
1994
15 years 7 months ago
Control Knowledge to Improve Plan Quality
Generating production-quality plans is an essential element in transforming planners from research tools into real-world applications. However most of the work to date on learning...
M. Alicia Pérez, Jaime G. Carbonell
ICML
1996
IEEE
16 years 7 months ago
Representing and Learning Quality-Improving Search Control Knowledge
Generating good, production-quality plans is an essential element in transforming planners from research tools into real-world applications, but one that has been frequently overl...
M. Alicia Pérez