801 search results - page 90 / 161 » The Inefficiency of Batch Training for Large Training Sets |
ICPR
2008
IEEE
14 years 10 months ago
2008
IEEE
This paper addresses the limitation of current multilinear PCA based techniques, in terms of prohibitive computational cost of testing and poor generalisation in some scenarios, w...
ICIP
2009
IEEE
14 years 10 months ago
2009
IEEE
An unsupervised seabed segmentation algorithm for synthetic aperture sonar (SAS) imagery is proposed. Each 2 m ? 2 m area of seabed is treated as a unique data point. A set of fea...
ICML
2009
IEEE
14 years 9 months ago
2009
IEEE
The kernel Perceptron is an appealing online learning algorithm that has a drawback: whenever it makes an error it must increase its support set, which slows training and testing ...
ICML
2008
IEEE
14 years 9 months ago
2008
IEEE
Recently, many applications for Restricted Boltzmann Machines (RBMs) have been developed for a large variety of learning problems. However, RBMs are usually used as feature extrac...
SIGMOD
2008
ACM
14 years 9 months ago
2008
ACM
Domain adaptation refers to the process of adapting an extraction model trained in one domain to another related domain with only unlabeled data. We present a brief survey of exis...