Title :
A comparison of two eigen-networks
Author :
Palmieri, Francesco ; Zhu, Jie
Author_Institution :
Dept. of Electr. & Syst. Eng., Connecticut Univ., Storrs, CT, USA
Abstract :
The authors compare two linear networks which project adaptively the input data points on their principal components. They rederive Sanger´s algorithm as the result of a constrained optimization problem and compare it to the cascaded network suggested by P. Foldiak (1989). It is shown how the two approaches are asymptotically equivalent. The cascaded network does not require any backpropagation, seems to be faster, and perhaps could be more easily implemented in real hardware
Keywords :
adaptive systems; eigenvalues and eigenfunctions; neural nets; Sanger´s algorithm; adaptive systems; cascaded network; constrained optimization; eigen-networks; input data points; linear networks; machine learning; neural nets; Algorithm design and analysis; Data engineering; Decorrelation; Eigenvalues and eigenfunctions; Jacobian matrices; Matrix decomposition; Nonlinear filters; Signal processing algorithms; Stochastic processes; Symmetric matrices;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155337
