Advertisement

Variable Selection in the Cascade-Correlation Learning Architecture

  • Igor V. Tetko
  • Vasyl V. Kovalishyn
  • Alexander I. Luik
  • Tamara N. Kasheva
  • Alessandro E. P. Villa
  • David J. Livingstone

Abstract

Recently there has been a growing interest in the application of neural networks in the field of QSAR. It was demonstrated that this method is often superior to the traditional approaches.1 Other studies have shown that prediction ability of such methods can be substantially improved if the number of input variables for neural networks is optimized.2,3

Keywords

Neural Network Petroleum Chemistry Generalization Ability Prediction Ability Neural Network Algorithm 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    D. Maddalena, Applications of artificial neural networks to quantitative structure-activity relationships, Exp. Opin. Thee. Patents. 6: 239–251 (1996).CrossRefGoogle Scholar
  2. 2.
    I.V. Tetko, A.E.P. Villa, and D.J. Livingstone, Neural network studies. 2. Variable selection, J. Chem. Inf. Comput. Sci. 36: 794–803 (1996).CrossRefGoogle Scholar
  3. 3.
    D.J. Maddalena and S.A.R. Johnston, Prediction of receptor properties and binding affinity of ligands to benzodiazepines/gabaa receptors using artificial neural networks, J. Med. Chem. 38: 715–724 (1995).CrossRefGoogle Scholar
  4. 4.
    S. Demon, E. Bienenstock, and R. Dourstat, Neural networks and the bias/variance dilemma, Neural Computation 4: 1–58 (1992).CrossRefGoogle Scholar
  5. 5.
    I.V. Tetko, D.T. Livingstone, and A.I. Luik, Neural network studies. I. Comparison of overfitting and overtraining, J. Chem. Inf. Comput. Sri. 35: 826–833 (1995).CrossRefGoogle Scholar
  6. 6.
    T. Ash and G. Cottrell, Topology-modifying neural network algorithms, in: The Handbook of Brain Theory and Neural Networks, M.A. Arbib, ed., MIT, Cambridge, (1995).Google Scholar
  7. 7.
    S.E. Fahlman and C. Lebiere, The cascade-correlation learning architecture, in: NIPS°2, D.S. Touretzky, cd., Morgan-Kaufmann, San Mateo (1990).Google Scholar
  8. 8.
    V.V. Kovalishyn, LV. Tetko, A.I. Luik, V.V. Kholodovych, A.E.P. Villa, and D.J. Livingstone, Neural network studies. 3. Variable selection in the cascade-correlation learning architecture, J. Chem. Inf. Comput. Sci. 38: 651–659 (1998).CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2000

Authors and Affiliations

  • Igor V. Tetko
    • 1
    • 2
  • Vasyl V. Kovalishyn
    • 1
  • Alexander I. Luik
    • 1
  • Tamara N. Kasheva
    • 1
  • Alessandro E. P. Villa
    • 2
  • David J. Livingstone
    • 3
    • 4
  1. 1.Institute of Bioorganic & Petroleum ChemistryKyivUkraine
  2. 2.Institut de PhysiologieLausanneSwitzerland
  3. 3.ChemQuest, Cheyney HouseSteeple Morden, HertsUK
  4. 4.Centre for Molecular designUniversity of PortsmouthHantsUK

Personalised recommendations