1393 search results - page 164 / 279 » Machine Learning by Function Decomposition |
109
Voted
GECCO
2006
Springer
15 years 5 months ago
2006
Springer
The representation used by a learning algorithm introduces a bias which is more or less well-suited to any given learning problem. It is well known that, across all possible probl...
108
click to vote
IJCNN
2006
IEEE
15 years 7 months ago
2006
IEEE
Abstract— Making inferences and choosing appropriate responses based on incomplete, uncertainty and noisy data is challenging in financial settings particularly in bankruptcy de...
124
click to vote
ICML
2008
IEEE
16 years 2 months ago
2008
IEEE
In this paper we show how common speech recognition training criteria such as the Minimum Phone Error criterion or the Maximum Mutual Information criterion can be extended to inco...
113
click to vote
ECCV
2006
Springer
16 years 3 months ago
2006
Springer
The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
131
click to vote
AMAST
2004
Springer
15 years 7 months ago
2004
Springer
concerns, abstraction (particularly hierarchical abstraction), simplicity, and restricted visibility (locality of information). The overall goal behind these principles was stated ...