A computational study on the performance of artificial neural networks under changing structural design and data distribution

DOI10.1016/S0377-2217(01)00085-6zbMath1007.90018OpenAlexW2061873162MaRDI QIDQ1600897

Parag C. Pendharkar

Publication date: 16 June 2002

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0377-2217(01)00085-6

zbMATH Keywords

discriminant analysisartificial neural networks

Mathematics Subject Classification ID

Reliability, availability, maintenance, inspection in operations research (90B25) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items

A threshold-varying artificial neural network approach for classification and its application to bankruptcy prediction problem ⋮ An empirical study of impact of crossover operators on the performance of non-binary genetic algorithm based neural approaches for classification. ⋮ Forecasting business profitability by using classification techniques: a comparative analysis based on a Spanish case ⋮ A data mining-constraint satisfaction optimization problem for cost effective classification

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An experimental evaluation of neural networks for classification
• Quantifying inductive bias: AI learning algorithms and Valiant's learning framework
• Optimization of neural networks: A comparative analysis of the genetic algorithm and simulated annealing
• New LP based heuristics for the classification problem
• Adaptive regularization parameter selection method for enhancing generalization capability of neural networks
• Global optimization for artificial neural networks: A tabu search application
• A general lower bound on the number of examples needed for learning
• Using Feature Construction to Improve the Performance of Neural Networks
• Linear Discriminant Functions Determined by Genetic Search
• Managerial Applications of Neural Networks: The Case of Bank Failure Predictions
• A Study of Composite or Hybrid Classifiers for Knowledge Discovery
• Learning representations by back-propagating errors