An adaptive method of training multilayer perceptrons

Proceedings of the International Joint Conference on Neural Networks

Volumn 3, Issue , 2001, Pages 2013-2018

  Lo, J T ^a   Bassu, D ^a  

^a UNIVERSITY OF MARYLAND   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE SYSTEMS; APPROXIMATION THEORY; FUNCTION EVALUATION; LEARNING SYSTEMS; SENSITIVITY ANALYSIS;

ADAPTIVE TRAINING; FUNCTION APPROXIMATION; SENSITIVITY INDEX;

MULTILAYER NEURAL NETWORKS;

EID: 0034862852     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. Approximation by superpositions of a sigmoidal function
2. On the approximate realization of continuous mappings by neural networks
3. State-space formulae for all stabilizing controllers that satisfy an h-infinity norm bound and relations to risk-sensitivity
4. H-infinity optimality criteria for lms and back propagation
5. Multilayer feedforward networks are universal approximators
6. Optimal stochastic linear systems with exponential performance criteria and their relation to deterministic games
7. Robust estimation and failure detection for linear systems
8. Optimization of stochastic linear systems with additive measurement and process noise using exponential performance criteria
9. Optimal stochastic estimation with exponential cost criteria
10. Beyond regression: New tools for prediction and analysis in the behavioral sciences