Structure adaptation in artificial neural networks through adaptive clustering and through growth in state space

  • Andrés Pérez-Uribe
  • Eduardo Sanchez
Plasticity Phenomena (Maturing, Learning & Memory)
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1606)


There is a growing evidence that the human brain follows an environmentally-guided neural circuit building that increases its learning flexibility. Similarly, it has been shown that artificial neural networks with dynamic topologies attempt to overcome the problem of determining the appropriate topology to optimally solve a given application. This paper presents a modular structure-adaptable artificial neural network architecture for autonomous control systems consisting of an unsupervised learning network, a reinforcement learning module and a planning module. Finally, we present an extension of the state representation of the environment by introducing short-term memories to deal with the problem of partial observability in the real-world.


Artificial neural networks topology adaptation reinforcement learning neurocontrol autonomous mobile robots partially observable environments 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    A.E. Alpaydin. Neural Models of Incremental Supervised and Unsupervised Learning. PhD thesis, Swiss Federal Institute of Technology, Lausanne, 1990. These 863.Google Scholar
  2. 2.
    T. Ash and G. Cottrell. Topology-modifying neural network algorithms. In Michael A. Arbib, editor, Handbook of Brain Theory and Neural Networks, pages 990–993. MIT Press, 1995.Google Scholar
  3. 3.
    A.G. Barto. Reinforcement learning in motor control. In Michael A. Arbib, editor, Handbook of Brain Theory and Neural Networks, pages 809–812. MIT Press, 1995.Google Scholar
  4. 4.
    M. Bishop-Ring. Continual learning in reinforcement environments. PhD thesis, The University of Texas at Austin, August 1994.Google Scholar
  5. 5.
    G. Carpenter and S. Grossberg. The ART of Adaptive Pattern Recognition by a self-organizing neural network. IEEE Computer, pages 77–88, March 1988.Google Scholar
  6. 6.
    E. Fiesler. Comparative bibliography of ontogenic neural networks. Proceedings of the International Conference on Artificial Neural Networks (ICANN’94), 1994.Google Scholar
  7. 7.
    B. Fritzke. Unsupervised ontogenic networks. In Handbook of Neural Computation, pages C2.4:1–C2.4:16. Institute of Physics Publishing and Oxford University Press, 1997.Google Scholar
  8. 8.
    S. Grossberg. The link between brain learning, attention and conciousness. Technical Report CAS/CNS-TR-97-018, Department of Cognitive and Neural Systems, Boston University, June 1998. (to appear in Conciousness and Cognition).Google Scholar
  9. 9.
    T. Kohonen. Self-Organizing Maps, volume 30. Springer Series in Information Sciences, april 1995.Google Scholar
  10. 10.
    L. Kuvayev and R. Sutton. Approximation in model-based learning. In Proceedings of the ICML’97 Workshop on Modelling in Reinforcement Learning, Vanderbilt University, July 1997.Google Scholar
  11. 11.
    J.L. Lin and T.M. Mitchell. Reinforcement learning with hidden states. In J-A. Meyer, H.L. Roitblat, and S.W. Wilson, editors, From Animals to Animats: Proceedings of the Second Intl. Conf. on Simulation of Adaptive Behavior, 1992.Google Scholar
  12. 12.
    F. Mondada, E. Franzi, and P. Ienne. Mobile robot miniaturization: A tool for investigat ing in control algorithms. In Proceedings of the Third International Symposium on Experimen tal Robotics, Kyoto, Japan, 1993.Google Scholar
  13. 13.
    A. Pérez-Uribe and E. Sanchez. FPGA Implementation of an Adaptable-Size Neural Network. In Proceedings of the International Conference on Artificial Neural Networks ICANN96, pages 383–388, Springer Verlag, July 1996.Google Scholar
  14. 14.
    A. Pérez-Uribe and E. Sanchez. Structure-Adaptable Neurocontrollers: A Hardware-Friendly Approach. In J. Mira, R. Moreno-Díaz, and J. Cabestany, editors, Biological and Artificial Computation: From Neuroscience to technology, pages 1251–1259, Lecture Notes in Computer Science 1240, Springer Verlag, 1997.Google Scholar
  15. 15.
    A. Pérez-Uribe and E. Sanchez. A Comparison of Reinforcement Learning with Eligibility Traces and Integrated Learning, Planning and Reacting. In Proceedings of the International Conference on Computational Intelligence for Modelling Control and Automation, 1999. (to appear).Google Scholar
  16. 16.
    A. Pérez-Uribe and E. Sanchez. A Digital Artificial Brain Architecture for Mobile Autonomous Robots. In M. Sugisaka and H. Tanaka, editors, Proceedings of the Fourth International Symposium on Artificial Life and Robotics AROB’99, pages 240–243, Oita, Japan, 1999.Google Scholar
  17. 17.
    S. R. Quartz and T. J. Sejnowski. The neural basis of cognitive development: A constructivism manifesto. Behavioral and Brain Sciences, 20(4):537+, December 1997.Google Scholar
  18. 18.
    S. Schaal and C.G. Atkenson. Constructive incremental learning from only local information. Neural Computation, 10(8):2047–2084, 1998.CrossRefGoogle Scholar
  19. 19.
    R.S. Sutton. Integrated architectures for Learning, Planning, and Reacting based on approximating Dynamic Programming. In Morgan Kaufmann, editor, Proceedings of the Seventh International Conference on Machine Learning, pages 216–224, 1990.Google Scholar
  20. 20.
    R.S. Sutton. Generalization in reinforcement learning: Successful examples using sparse coarse coding. In MIT Press, editor, Advances in Neural Information Processing Systems 8, pages 1038–1044, 1996.Google Scholar
  21. 21.
    R.S. Sutton and A.G. Barto. Reinforcement Learning: An Introduction. MIT Press, 1998.Google Scholar
  22. 22.
    C. Watkins and P. Dayan. Technical note q-learning. Machine Learning, 8:279–292, 1992.MATHGoogle Scholar
  23. 23.
    S.D. Whitehead and D.H. Ballard. Active perception and reinforcement learning. In Proceedings of the Seventh Intl. Conf. on Machine Learning, Austin, 1990.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Andrés Pérez-Uribe
    • 1
  • Eduardo Sanchez
    • 1
  1. 1.Logic Systems Laboratory, Computer Science DepartmentSwiss Federal Institute of TechnologyLausanneSwitzerland

Personalised recommendations