Sciweavers

77 search results - page 11 / 16
» Natural methods for robot task learning: instructive demonst...
Sort
View
EH
1999
IEEE
351views Hardware» more  EH 1999»
13 years 12 months ago
Evolvable Hardware or Learning Hardware? Induction of State Machines from Temporal Logic Constraints
Here we advocate an approach to learning hardware based on induction of finite state machines from temporal logic constraints. The method involves training on examples, constraint...
Marek A. Perkowski, Alan Mishchenko, Anatoli N. Ch...
ICRA
2003
IEEE
165views Robotics» more  ICRA 2003»
14 years 25 days ago
Multi-robot task-allocation through vacancy chains
Existing task allocation algorithms generally do not consider the effects of task interaction, such as interference, but instead assume that tasks are independent. That assumptio...
Torbjørn S. Dahl, Maja J. Mataric, Gaurav S...
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
14 years 1 months ago
Co-evolving recurrent neurons learn deep memory POMDPs
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
Faustino J. Gomez, Jürgen Schmidhuber
ICML
2005
IEEE
14 years 8 months ago
Recognition and reproduction of gestures using a probabilistic framework combining PCA, ICA and HMM
This paper explores the issue of recognizing, generalizing and reproducing arbitrary gestures. We aim at extracting a representation that encapsulates only the key aspects of the ...
Sylvain Calinon, Aude Billard
SIGCSE
2008
ACM
143views Education» more  SIGCSE 2008»
13 years 7 months ago
Test-driven learning in early programming courses
Coercing new programmers to adopt disciplined development practices such as thorough unit testing is a challenging endeavor. Test-driven development (TDD) has been proposed as a s...
David Janzen, Hossein Saiedian