Functional Link Artificial Neural Networks Filter for Gaussian Noise

DOI

10.2991/iccsee.2013.510How to use a DOI?

Keywords

FLANN, BPNN, Denoising, Gaussian noise

Abstract

In this paper, FLANN(functional link ANN) filter is presented for Gaussian noise. FLANN is a singer layer with expanded input vectors and has lower computational cost than MLP(multilayer perceptron). Three types of functional expansion are discussed. BP(back propagation algorithm) for nonlinear activation function and matrix calculation for identical activation function are exploited for training FLANN. Simulation shows that convergence is not guaranteed in BP and related to the initial weight matrix and training images, and that linear FLANN trained by matrix calculation performs better than both nonlinear FLANN trained by BP and Wiener filter in detail region in environment of Gaussian noise

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yuanhua Guo
AU  - Chunlun Huang
PY  - 2013/03
DA  - 2013/03
TI  - Functional Link Artificial Neural Networks Filter for Gaussian Noise
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 2027
EP  - 2031
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.510
DO  - 10.2991/iccsee.2013.510
ID  - Guo2013/03
ER  -