Slow feature discriminant analysis and its application on handwritten digit recognition

Authors:
Yaping Huang;Jiali Zhao;Mei Tian;Qi Zou;Siwei Luo
Affiliations:
Department of Computer Engineering, The Beijing Jiaotong University, Beijing, China;Department of Computer Engineering, The Beijing Jiaotong University, Beijing, China;Department of Computer Engineering, The Beijing Jiaotong University, Beijing, China;Department of Computer Engineering, The Beijing Jiaotong University, Beijing, China;Department of Computer Engineering, The Beijing Jiaotong University, Beijing, China
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 9
Cited 0

Connectionist learning procedures

Artificial Intelligence
Learning invariance from transformation sequences

Neural Computation
Slow feature analysis: unsupervised learning of invariances

Neural Computation
Simple-cell-like receptive fields maximize temporal coherence in natural video

Neural Computation
Best Practices for Convolutional Neural Networks Applied to Visual Document Analysis

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Learning viewpoint invariant object representations using a temporal coherence principle

Biological Cybernetics
A trainable feature extractor for handwritten digit recognition

Pattern Recognition
Deformation Models for Image Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Removing time variation with the anti-hebbian differential synapse

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Slow Feature Analysis (SFA) is an unsupervised algorithm by extracting the slowly varying features from time series and has been used to pattern recognition successfully. Based on SFA, this paper develops a new algorithm, Slow Feature Discriminant Analysis (SFDA), which can maximize the temporal variation of between-class time series, and minimize the temporal variation of within-class time series simultaneously. Due to adoption of discrimination power, the performance on pattern recognition is improved compared to SFA. The experiments results on MNIST digit handwritten database also show that the proposed algorithm is in particular attractive.