801 search results - page 138 / 161 » The Inefficiency of Batch Training for Large Training Sets |
AAAI
2010
13 years 7 months ago
2010
Multi-task learning aims at combining information across tasks to boost prediction performance, especially when the number of training samples is small and the number of predictor...
AHS
2007
IEEE
13 years 7 months ago
2007
IEEE
Online incremental evolution for a complex high-speed pattern recognition architecture has been implemented on a Xilinx Virtex-II Pro FPGA. The fitness evaluation module is entir...
IJCV
2008
13 years 7 months ago
2008
Abstract We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our ...
IJCV
2000
13 years 7 months ago
2000
This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes a...
IDA
2002
Springer
13 years 7 months ago
2002
Springer
This paper introduces a strategy for training ensemble classifiers by analysing boosting within margin theory. We present a bound on the generalisation error of ensembled classifi...