1136 search results - page 60 / 228 » Learning with Weighted Transducers |
NIPS
1994
13 years 10 months ago
1994
We present efficient algorithms for dealing with the problem of missing inputs (incomplete feature vectors) during training and recall. Our approach is based on the approximation ...
ICML
2004
IEEE
14 years 10 months ago
2004
IEEE
We present a generalization of the nonnegative matrix factorization (NMF), where a multilayer generative network with nonnegative weights is used to approximate the observed nonne...
GECCO
2010
Springer
13 years 10 months ago
2010
Springer
This paper presents an integrated approach, combining a state-of-the-art commercial object detection system and genetic algorithms (GA)-based learning for automatic object classif...
AAAI
2012
11 years 11 months ago
2012
Kernel methods have been successfully applied to many machine learning problems. Nevertheless, since the performance of kernel methods depends heavily on the type of kernels being...
WWW
2006
ACM
14 years 9 months ago
2006
ACM
In this paper we describe a solution for incorporating background knowledge into the OntoGen system for semi-automatic ontology construction. This makes it easier for different us...