Sciweavers

641 search results - page 100 / 129
» Training Methods for Adaptive Boosting of Neural Networks
Sort
View
MLDM
2001
Springer
15 years 2 months ago
Local Learning Framework for Recognition of Lowercase Handwritten Characters
Abstract. This paper proposes a general local learning framework to effectively alleviate the complexities of classifier design by means of “divide and conquer” principle and ...
Jian-xiong Dong, Adam Krzyzak, Ching Y. Suen
IJCNN
2008
IEEE
15 years 4 months ago
Incremental Common Spatial Pattern algorithm for BCI
— A major challenge in applying machine learning methods to Brain-Computer Interfaces (BCIs) is to overcome the on-line non-stationarity of the data blocks. An effective BCI syst...
Qibin Zhao, Liqing Zhang, Andrzej Cichocki, Jie Li
ICANN
2003
Springer
15 years 2 months ago
Weighted Self-Organizing Maps: Incorporating User Feedback
One interesting way of accessing collections of multimedia objects is by methods of visualization and clustering. Growing self-organizing maps provide such a solution, which adapts...
Andreas Nürnberger, Marcin Detyniecki
IAT
2008
IEEE
14 years 9 months ago
Scaling Up Multi-agent Reinforcement Learning in Complex Domains
TD-FALCON (Temporal Difference - Fusion Architecture for Learning, COgnition, and Navigation) is a class of self-organizing neural networks that incorporates Temporal Difference (...
Dan Xiao, Ah-Hwee Tan
JMLR
2012
13 years 3 days ago
Krylov Subspace Descent for Deep Learning
In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In ou...
Oriol Vinyals, Daniel Povey