Sciweavers

154 search results - page 4 / 31
» Representing and Learning Quality-Improving Search Control K...
Sort
View
JMLR
2002
117views more  JMLR 2002»
14 years 11 months ago
Learning to Construct Fast Signal Processing Implementations
A single signal processing algorithm can be represented by many mathematically equivalent formulas. However, when these formulas are implemented in code and run on real machines, ...
Bryan Singer, Manuela M. Veloso
IJCNN
2008
IEEE
15 years 6 months ago
Building meta-learning algorithms basing on search controlled by machine complexity
Abstract— Meta-learning helps us find solutions to computational intelligence (CI) challenges in automated way. Metalearning algorithm presented in this paper is universal and m...
Norbert Jankowski, Krzysztof Grabczewski
MMB
2012
Springer
259views Communications» more  MMB 2012»
13 years 7 months ago
Boosting Design Space Explorations with Existing or Automatically Learned Knowledge
Abstract. During development, processor architectures can be tuned and configured by many different parameters. For benchmarking, automatic design space explorations (DSEs) with h...
Ralf Jahr, Horia Calborean, Lucian Vintan, Theo Un...
IJCAI
2001
15 years 29 days ago
Robot Weightlifting By Direct Policy Search
This paper describes a method for structuring a robot motor learning task. By designing a suitably parameterized policy, we show that a simple search algorithm, along with biologi...
Michael T. Rosenstein, Andrew G. Barto
ICML
2001
IEEE
16 years 12 days ago
Learning to Generate Fast Signal Processing Implementations
A single signal processing algorithm can be represented by many mathematically equivalent formulas. However, when these formulas are implemented in code and run on real machines, ...
Bryan Singer, Manuela M. Veloso