Title :
Feedforward neural network´s denoising with wavelet basis
Author :
Jianwei, Li ; Chengge, Zhong ; Huachun, Dong ; Taifan, Quan
Author_Institution :
Dept. of Electron. & Commun. Eng., Harbin Inst. of Technol., China
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
Keywords :
correlation methods; feedforward neural nets; interference suppression; learning (artificial intelligence); noise; signal sampling; wavelet transforms; feedforward neural networks; learning samples; sampling noise; wavelet bases; wavelet basis; wavelet transform theory; Computational Intelligence Society; Feedforward neural networks; Neural networks; Noise reduction; Quantization; Quantum mechanics; Sampling methods; Signal mapping; Signal processing; Training data;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.566565
