Sciweavers

2750 search results - page 65 / 550
» The complexity of learning SUBSEQ(A)
Sort
View
ICML
2007
IEEE
16 years 7 months ago
CarpeDiem: an algorithm for the fast evaluation of SSL classifiers
In this paper we present a novel algorithm, CarpeDiem. It significantly improves on the time complexity of Viterbi algorithm, preserving the optimality of the result. This fact ha...
Roberto Esposito, Daniele P. Radicioni
KCAP
2005
ACM
15 years 11 months ago
Knowledge transfer via advice taking
We present a framework for knowledge transfer from one reinforcement learning task to a related task through advicetaking mechanisms. We discuss the importance of transfer in comp...
Lisa Torrey, Trevor Walker, Jude W. Shavlik, Richa...
GECCO
2007
Springer
174views Optimization» more  GECCO 2007»
15 years 10 months ago
Classifier systems that compute action mappings
The learning in a niche based learning classifier system depends both on the complexity of the problem space and on the number of available actions. In this paper, we introduce a ...
Pier Luca Lanzi, Daniele Loiacono
IJHIS
2008
84views more  IJHIS 2008»
15 years 6 months ago
Selective generation of training examples in active meta-learning
Meta-Learning has been successfully applied to acquire knowledge used to support the selection of learning algorithms. Each training example in Meta-Learning (i.e. each meta-exampl...
Ricardo Bastos Cavalcante Prudêncio, Teresa ...
COCO
2010
Springer
153views Algorithms» more  COCO 2010»
15 years 10 months ago
Communication Complexity with Synchronized Clocks
Abstract—We consider two natural extensions of the communication complexity model that are inspired by distributed computing. In both models, two parties are equipped with synchr...
Russell Impagliazzo, Ryan Williams