An optimal dimension expansion procedure for obtaining linearly separable subsets
Resource
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Journal
IEEE International Joint Conference on Neural Networks
Pages
2461-2465
Date Issued
1991-11
Date
1991-11
Author(s)
Tseng, Yuen-Hsien
DOI
N/A
Abstract
The authors study the necessary and sufficient condition for linearly separable subsets and then propose an optimal dimension expansion procedure that makes any mapping to be performed by perceptrons learnable by an error-correction procedure. For n-bit parity check problems, it is shown that only one additional dimension is augmented to make them solvable by single-layer perceptrons. Other applications such as for decoding error-correcting codes are also considered.>
SDGs
Type
conference paper
File(s)![Thumbnail Image]()
Loading...
Name
00170758.pdf
Size
211.81 KB
Format
Adobe PDF
Checksum
(MD5):3c3477200b2e9a33a520a742d34fd136