Title :
Adaptive structures with algebraic loops
Author :
Lamego, Marcelo Malini
Author_Institution :
Masimo Corp., Irvine, CA, USA
fDate :
1/1/2001 12:00:00 AM
Abstract :
The contraction theorem has many fields of application, including linear algebraic equations, differential and integral equations, control systems theory, optimization, etc. The paper aims at showing how contraction mapping can be applied to the computation and the training of adaptive structures with algebraic loops. These structures are used for the approximation of unknown functional relations (mappings) represented by training sets. The technique is extended to multilayer neural networks with algebraic loops. Application of a two-layer neural network to breast cancer diagnosis is described
Keywords :
Lyapunov methods; adaptive systems; algebra; function approximation; learning (artificial intelligence); multilayer perceptrons; set theory; adaptive structures; algebraic loops; breast cancer diagnosis; contraction mapping; contraction theorem; multilayer neural networks; two-layer neural network; Adaptive systems; Approximation methods; Breast cancer; Control systems; Delay; Differential algebraic equations; Integral equations; Multi-layer neural network; Neural networks; Neurofeedback;
Journal_Title :
Neural Networks, IEEE Transactions on
