Feedforward neural network's denoising with wavelet basis

Authors :: Quan Taifan
Li Jianwei
Zhong Chengge
Dong Huachun
Source :: Proceedings of Third International Conference on Signal Processing (ICSP'96).
Publication Year :: 2002
Publisher :: IEEE, 2002.
Abstract: Methods based on wavelet transform theory for decreasing sampling noise in feedforward neural networks are proposed in this paper. Wavelet bases are employed in the network to constrain the network's ability in learning samples which are corrupted by noise. The selection of the wavelet bases which correlate with the map to be approximated is mainly discussed.

Subjects :: Discrete wavelet transform
Lifting scheme
Time delay neural network
business.industry
Computer science
Noise reduction
Second-generation wavelet transform
Stationary wavelet transform
Wavelet transform
Cascade algorithm
Pattern recognition
Data_CODINGANDINFORMATIONTHEORY
Wavelet packet decomposition
Probabilistic neural network
Wavelet
Feedforward neural network
Artificial intelligence
business

Database :: OpenAIRE
Journal :: Proceedings of Third International Conference on Signal Processing (ICSP'96)
Accession number :: edsair.doi...........46f37526af1599727066e3ccbe698ce2
Full Text :: https://doi.org/10.1109/icsigp.1996.566565