Skip to main content
Log in

Neurocontrol: Recent advances and links with the human brain

  • Published:
AI & SOCIETY Aims and scope Submit manuscript

Abstract

One of the aims in the AI research, is to understand the principles and mechanisms of intelligence in the human brain. Definitely the brain is a neurocontroller, a collection of neurons which learn to output the right actions or decisions over time. This paper describes recent neurocontrol designs which are considered the state-of-the-art for intelligent control and their plausibility as models of the human brain.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Astrom, K. J. (1988). Towards intelligent control.IEEE Control Systems Magazine.

  • Barto, A. G., Sutton, R. S., and Anderson, C. W. (1983). Neuronlike adaptive elements that can solve difficult control problems.IEEE Transactions on Systems, Man and Cybernetics, SMC-13, 834–846.

    Google Scholar 

  • Bertsekas, D. P. and Tsitsiklis, J. N. (1996). Neuro-Dynamic Programming. Athena Scientific.

  • Carpenter, G. A. and Grossberg, S. (1990). Adaptive resonance theory: Neural network architectures for self-organizing pattern recognition. In Eckmiller, R., Hartmann, G., and Hauske, G., editors,Parallel Processing in Neural Systems and Computers, 383–389. Elsevier Science Publishers B.V. (North Holland).

  • Dracopoulos, D. C. (1997). Evolutionary Learning Algorithms for Neural Adaptive Control. Springer-Verlag.

  • Dracopoulos, D. C. and Jones, A. J. (1993). Neuromodels of analytic dynamic systems.Neural Computing & Applications, 1(4), 268–279.

    Article  MATH  Google Scholar 

  • Grossberg, S. (1997). personal communication.

  • Hertz, J., Kroph, A., and Palmer, R. G. (1991).Introduction to the Theory of Neural Computation. Addison Wesley.

  • Jordan, M. I. and Rumelhart, D. E. (1992). Forward Models: Supervised learning with a distal teacher.Cognitive Science, 16, 307–354.

    Article  Google Scholar 

  • Kawato, M. (1990). Computational schemes and neural network models for formation and control of multijoint arm trajectory. In Miller, S. and Werbos, editors,Neural Networks for Control. MIT Press.

  • Levine, D. S. (1996). Don’t just stand there, optimize something. In Levine, D. and Elsberry, W., editors,Optimality in Biological and Artificial Networks, Erlbaum. (1).

  • Mendel, J. M. and McLaren, R. W. (1970). Reinforcement learning control and pattern recognition systems. In Press, A., editor,Adaptive Learning and Pattern Recognition Systems, chapter 8. J. M. Mendel and K. S. Fu.

  • Miller, W., Sutton, R. S., and Werbos, P. J., editors (1990).Neural Networks for Control. MIT Press.

  • Narendra, K. S. (1992). Adaptive control of dynamical systems using neural networks. In White, D. A. and Sofge, D. A., editors,Handbook of Intelligent Control, Van Nostrand Reinhold, chapter 5.

  • Prokhorov, D. V. and Wunch II, D. C. (1996). Advanced adaptive critic designs. InWorld Congress on Neural Networks, San Diego, California, Lawrence Erlbaum Associates, Inc. and INNS Press. 83–87.

    Google Scholar 

  • Psaltis, D., Sideris, A., and Yamamura, A. A. (1988). A multilayered neural net work controller.IEEE Control Systems Magazine, 17–21.

  • Rumelhart, D., McClelland, J., and the PDP research group (1986).Parallel Distributed Processing-Explorations in the Microstructure Cognition, MIT Press. 1.

  • Simon, H. (1979).Models of Thought. Yale University Press.

  • Sloman, A. (1992). The mind as a control system. In Hookway, C. and Peterson, D., editors,Philosophy and the Cognitive Sciences, Proceedings of the 1992 Royal Institute of Philosophy Conference, Cambridge University Press. 69–110.

  • Sutton, R. S. and Barto, A. G. (1998).Reinforcement Learning: An Introduction. MIT Press/Bradford Books.

  • WCNN95 (1995). World Congress on Neural Networks. Lawrence Erlbaum Associates, Inc. and INNS Press.

  • WCNN96 (1996). World Congress on Neural Networks. Lawrence Erlbaum Associates, Inc. and INNS Press.

  • Werbos, P. (1990a). Neurocontrol and related techniques. In Maren, A., editor,Handbook of Neural Computing Applications, Academic Press. 345–381.

  • Werbos, P. J. (1990b). Backpropagation through time: What it does and how to do it.Proceedings of the IEEE, 78(10).

  • Werbos, P. J. (1996a). personal communication.

  • Werbos, P. J. (1996b). Learning in the brain: An engineering interpretation. In Pribram, K., editor,Learning as Self-Organization. Erlbaum.

  • Werbos, P. J. (1996c). Neurocontrol, biological intelligence and engineering applications: Evaluation and prognosis. In BMBFProceedings on Neuroinformatiks and AI, Berlin.

  • Werbos, P. J. (1996d). Optimization: A foundation for understanding consciousness. In Levine, D. and Elsberry, W., editors,Optimality in Biological and Artificial Networks, Erlbaum, chapter 1.

  • White, D. A. and Sofge, D. A., editors (1992).Handbook of Intelligent Control. Van Nostrand Reinhold.

  • Widrow, B., Gupta, N., and Maitra, S. (1973). Punish/reward: Learning with a critic in adaptive threshold systems.IEEE Transactions on Systems, Man and Cybernetics, volume 5.

  • Widrow, B. and Stearns, S. D. (1985).Adaptive Signal Processing. Prentice Hall, first edition.

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Dimitri C. Dracopoulos.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Dracopoulos, D.C. Neurocontrol: Recent advances and links with the human brain. AI & Soc 11, 63–75 (1997). https://doi.org/10.1007/BF02812439

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02812439

Keywords

Navigation