Convergence properties and stationary points of the two-layer backpropagation algorithm used for nonlinear function modeling

Proceedings of the International Joint Conference on Neural Networks

Volumn 1, Issue , 2001, Pages 638-643

  Ibnkahla, M ^a  

^a QUEEN S UNIVERSITY   (Canada)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; APPROXIMATION THEORY; BACKPROPAGATION; COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; FUNCTION EVALUATION; MATHEMATICAL MODELS; RECURSIVE FUNCTIONS; STATISTICAL METHODS; TRANSFER FUNCTIONS;

FUNCTION APPROXIMATION; MEAN SQUARED ERROR; NONLINEAR FUNCTION MODELING;

NEURAL NETWORKS;

EID: 0034844359     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Statistical analysis of a two-layer back propagation algorithm used for modeling non linear memoryless channels: The single neuron case
2. Multilayer feedforward networks are universal approximators
3. Applications of neural networks to digital communications: A survey
4. Neural network modeling and identification of non linear channels with memory: Algorithms, applications and analytic models
5. Neural networks for modeling non linear memoryless channels
6. Learning internal representations by error propagation