Title :
A complex valued Hebbian learning algorithm
Author :
De Castro, Maria Cristina Felippetto ; De Castro, Fernando César C ; Amaral, José Nelson ; Franco, Paulo Roberto G
Author_Institution :
Dept. of Electr. Eng., Univ. Catolica do Rio Grande do Sul, Porto Alegre, Brazil
Abstract :
We present a training rule for a single-layered linear network with complex valued weights and activation levels. This network can be used to extract the principal components of a complex valued data set. We also introduce a new training method that reduces the training time of the complex valued as well as of the real valued network. The use of the new network and training algorithm is illustrated with a problem of compressing images represented in the spectral domain
Keywords :
Hebbian learning; data compression; image coding; neural nets; complex activation levels; complex valued Hebbian learning algorithm; complex valued data set; complex valued weights; image compression; principal components; real valued network; single-layered linear network; spectral domain; training rule; Data mining; Eigenvalues and eigenfunctions; Hebbian theory; Image coding; Neural networks; Neurons; Principal component analysis; Radar applications; Sonar; Vectors;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.685950
