DocumentCode :
285192
Title :
High-order perceptrons for decoding error-correcting codes
Author :
Tseng, Yeun-Hsien ; WU, JA-LING
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
Volume :
3
fYear :
1992
fDate :
7-11 Jun 1992
Firstpage :
24
Abstract :
The authors prove that the single-error correcting (2n-1, 2n-1-n) Hamming code and its extended single-error correcting/double-error detecting (2n, 2n-1-n) code can be decoded by low-complexity single-layer perceptrons which use high-order polynomials as their discriminant functions. It is illustrated that multiple-error correcting codes can be decoded by two-layer networks with high-order perceptrons in the first layer and linear perceptrons in the second layer
Keywords :
decoding; error correction codes; neural nets; polynomials; Hamming code; decoding; error-correcting codes; high-order perceptrons; high-order polynomials; linear perceptrons; neural nets; two-layer networks; Backpropagation; Computer science; Costs; Decoding; Error correction codes; Hopfield neural networks; Law; Multilayer perceptrons; Neural networks; Polynomials;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
Type :
conf
DOI :
10.1109/IJCNN.1992.227042
Filename :
227042
Link To Document :
بازگشت