The spiked random neural network: nonlinearity, learning and approximation

Author

Gelenbe, Erol

Author_Institution

Dept. of Electr. & Comput. Eng., Duke Univ., Durham, NC, USA

fYear

1998

fDate

14-17 Apr 1998

Firstpage

14

Lastpage

19

Abstract

We summarize the theoretical foundations of the random neural network model (RNN) and of its learning algorithm, and present a relevant bibliography of its theory and applications. Many applications have resulted from this model, including its use in still image and video compression which has achieved compression ratios of up to 500:1 for moving gray-scale images, with 30db PSNR quality levels. Another application of the RNN is to image segmentation; the recurrent feature of the network has been used to extract precise morphometric information from magnetic resonance imaging (MRI) scans of the human brain. The RNN has also been successfully applied to optimization and image texture analysis and reconstruction

Keywords

approximation theory; bibliographies; image processing; learning (artificial intelligence); recurrent neural nets; MRI scans; PSNR quality levels; RNN; approximation; human brain scans; image segmentation; image texture analysis; image texture reconstruction; learning; magnetic resonance imaging; moving gray-scale images; nonlinearity; optimization; precise morphometric information extraction; recurrent neural network; spiked random neural network; still image compression; video compression; Bibliographies; Biological neural networks; Gray-scale; Image coding; Image segmentation; Magnetic resonance imaging; Neural networks; PSNR; Recurrent neural networks; Video compression;

fLanguage

English

Publisher

ieee

Conference_Titel

Cellular Neural Networks and Their Applications Proceedings, 1998 Fifth IEEE International Workshop on

Conference_Location

London

Print_ISBN

0-7803-4867-2

Type

conf

DOI

10.1109/CNNA.1998.685674

Filename

685674