A polynomial time algorithm for the construction and training of a class of multilayer perceptrons

Neural Networks

Volumn 6, Issue 4, 1993, Pages 535-545

  Roy, Asim ^a   Kim, Lark Sang ^a   Mukhopadhyay, Somnath ^a  

^a ARIZONA STATE UNIVERSITY   (United States)

Author keywords

Classification algorithm; Clustering; Linear programming; Multilayer perceptrons; Net design; Polynomial time algorithm; Supervised learning

Indexed keywords

ALGORITHMS; CLASSIFICATION (OF INFORMATION); COMPUTATIONAL COMPLEXITY; COMPUTER AIDED DIAGNOSIS; COMPUTER VISION; LEARNING SYSTEMS; LINEAR PROGRAMMING; SPEECH RECOGNITION;

CLASSIFICATION ALGORITHM; CLUSTERING; MULTILAYER PERCEPTRONS; NET DESIGN; POLYNOMIAL TIME ALGORITHMS; SUPERVISED LEARNING;

NEURAL NETWORKS;

EID: 0027259956     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(05)80057-7     Document Type: Article

References (29)

1. ART 2: Self-organization of stable category recognition codes for analog input patterns
2. A linear programming approach to the discriminant problem
3. Evaluating alternative linear programming models to solve the two-group discriminant problem
4. Learning, invariance, and generalization in high-order networks
5. A new class of models for the discriminant problem
6. Analysis of hidden units in a layered network trained to classify sonar targets
7. Neural net and traditional classifiers
8. A new polynomial time algorithm for linear programming
9. A polynomial algorithm in linear programming
10. An introduction to neural computing
11. Neural network classifiers for speech recognition
12. Linear and nonlinear separation of patterns by linear programming
13. Pattern recognition via linear programming: Theory and application to medical diagnosis
14. Control methods used in a study of vowels
15. Induction of decision trees
16. A neural model for category learning
17. Pattern classification using linear programming
18. Pattern classifier design by linear programming
19. A statistical method for evaluating systematic relationships