Sciweavers

818 search results - page 77 / 164
» Regularized multi--task learning
Sort
View
ICANN
2009
Springer
14 years 4 months ago
Measuring and Optimizing Behavioral Complexity for Evolutionary Reinforcement Learning
Model complexity is key concern to any artificial learning system due its critical impact on generalization. However, EC research has only focused phenotype structural complexity ...
Faustino J. Gomez, Julian Togelius, Jürgen Sc...
ISCAS
2008
IEEE
169views Hardware» more  ISCAS 2008»
14 years 4 months ago
Sigma-delta learning for super-resolution independent component analysis
— Many source separation algorithms fail to deliver robust performance in presence of artifacts introduced by cross-channel redundancy, non-homogeneous mixing and highdimensional...
Amin Fazel, Shantanu Chakrabartty
CEAS
2004
Springer
14 years 3 months ago
Filtron: A Learning-Based Anti-Spam Filter
Abstract. We present Filtron, a prototype anti-spam filter that integrates the main empirical conclusions of our comprehensive analysis on using machine learning to construct eff...
Eirinaios Michelakis, Ion Androutsopoulos, Georgio...
DAGM
2004
Springer
14 years 3 months ago
Learning with Distance Substitution Kernels
Abstract. During recent years much effort has been spent in incorporating problem specific a-priori knowledge into kernel methods for machine learning. A common example is a-prior...
Bernard Haasdonk, Claus Bahlmann
ATVA
2006
Springer
153views Hardware» more  ATVA 2006»
14 years 1 months ago
Learning-Based Symbolic Assume-Guarantee Reasoning with Automatic Decomposition
Abstract. Compositional reasoning aims to improve scalability of verification tools by reducing the original verification task into subproblems. The simplification is typically bas...
Wonhong Nam, Rajeev Alur