Advertisement

Genetic Algorithms as Heuristics for Optimizing ANN Design

  • E. Alba
  • J. F. Aldana
  • J. M. Troya

Abstract

The problem of the ANN design is usually thought as residing in solving the training problem for some predefined ANN structure and connectivity. Training methods are very problem and ANN dependent. They are sometimes very accurate procedures but they work in narrow and restrictive domains. Thus the designer is faced to a wide diversity of different training mechanisms. We have selected Genetic Algorithms because of their robustness and their potential extension to train any ANN type. Furthermore we have addressed the connectivity and structure definition problems in order to accomplish a full genetic ANN design. These three levels of design can work in parallel, thus achieving multilevel relationships to build better ANNs. GRIAL is the tool used to test several new and known genetic techniques and operators. PARLOG is the Concurrent Logic Language used for the implementation in order to introduce new models for the genetic work and to attain an intralevel distributed search as well as to parallelize any ANN management and any genetic operations.

Keywords

Genetic Algorithm Hide Layer Genetic Operation Adaptive Mutation Hopfield Network 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    K.H. Kim, C.H. Lee, B.Y. Kim & H.Y. Hwang, ‘Neural Optimization network for minimum-via layer assignment’, Neurocomputing 3, 15–27, 1991.CrossRefGoogle Scholar
  2. [2]
    David E. Goldberg, ‘Genetic Algorithms in Search, Optimization & Machine Learning’, Addison-Wesley, 1989.Google Scholar
  3. [3]
    Darrell Whitley & Thomas Hanson, ‘Optimizing Neural Networks Using Faster, More Accurate Genetic Search’, Proceedings of the Third ICGA, Morgan Kaufmann, 391-396, 1989.Google Scholar
  4. [4]
    D. Whitley, T. Starkweather & C. Bogart, ‘Genetic Algorithms and Neural Networks: Optimizing Connections and Connectivity’, Parallel Computing 14, 347–361, 1990.CrossRefGoogle Scholar
  5. [5]
    H. Mühlenbein, ‘Limitations of multi-layer perceptron networks — steps towards genetic neural networks’, Parallel Computing 14, 249–260, 1990.CrossRefGoogle Scholar
  6. [6]
    H. Mühlenbein & J. Kindermann, ‘The Dynamics of Evolution and Learning — Towards Genetic Neural Networks’, Connectionism in Perspective, 173-197, 1989.Google Scholar
  7. [7]
    E. Alba Torres, J.F. Aldana Montes & J.M. Troya Linero, ‘Genetic Algorithms as Heuristics for Optimizing ANN Design’, Technical Report, Dpto Lenguajes y Ciencias de 1a Computación, Univ. de Málaga, 1992.Google Scholar
  8. [8]
    Lawrence Davis, ‘Bit-Climbing, Representational Bias and Test Suite Design’, Proceedings of the Fourth ICGA, Morgan Kaufmann, 18-23, 1991.Google Scholar
  9. [9]
    Kalyanmoy Deb & David E. Goldberg, ‘An Investigation of Niche and Species Formation in Genetic Function Optimization’, Proceedings of the Third ICGA, Morgan Kaufmann, 42-50, 1989.Google Scholar
  10. [10]
    Steven Alex Harp, Tariq Samad & Aloke Guha, Towards the Genetic Synthesis of Neural Networks’, Proceedings of the Third ICGA, Morgan Kaufmann, 360-369, 1989.Google Scholar
  11. [11]
    Keith Clark & Steve Gregory, ‘PARLOG: Parallel Programming in Logic’, ACM Trn. on PL & S 1-49, 1986.Google Scholar
  12. [12]
    Crammond, Davison, Burt, Huntbach & Lam, ‘The Parallel Parlog User Manual’, Imperial College, London, 1-40, 1989.Google Scholar
  13. [13]
    Darrel Whitley, ‘The GENITOR Algorithm and Selection Pressure: Why Rank-Based Allocation of Reproductive Trials is Best’, Proceedings of the Third ICGA, Morgan Kaufmann, 116-121, 1989.Google Scholar
  14. [14]
    Steven Alex Harp, Tariq Samad & Aloke Guha, ‘Towards the Genetic Synthesis of Neural Networks’, Proceedings of the Third ICGA, Morgan Kaufmann, 360-369, 1989.Google Scholar
  15. [15]
    J.M. Troya & J.F. Aldana, ‘Extending an Object Oriented Concurrent Logic Language for Neural Network Simulations’, IWANN, Lecture Notes in Computer Science, Springer-Verlag, 235-242, 1991.Google Scholar
  16. [16]
    D. Macfarlane & Ian East, ‘An investigation oj several Parallel genetic algorithms’, Univ. of Buckingham, MK 18 IEG, 60-67.Google Scholar

Copyright information

© Springer-Verlag/Wien 1993

Authors and Affiliations

  • E. Alba
    • 1
  • J. F. Aldana
    • 1
  • J. M. Troya
    • 1
  1. 1.Dpto. de Lenguajes y Ciencias de la Computación Facultad de InformáticaUniversidad de MálagaMálagaSpain

Personalised recommendations