Some Adaptive Advantages of the Ability to Make Predictions

  • Daniele Caligiore
  • Massimo Tria
  • Domenico Parisi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4095)


We describe some simple simulations showing two possible adaptive advantages of the ability to predict the consequences of one’s actions: predicted inputs can replace missing inputs and predicted success vs. failure can help deciding whether to actually executing a planned action or not. The neural networks controlling the organisms’ behaviour include distinct modules whose connection weights are all genetically inherited and evolved using a genetic algorithm except those of the predictive module which are learned during life.


Sensory Input Current Input Connection Weight Output Unit Average Fitness 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Blakemore, S.-J., Frith, C.D., Wolpert, D.M.: The cerebellum is involved in predicting the sensory consequences of action. NeuroReport 12, 1879–1884 (2001)CrossRefGoogle Scholar
  2. 2.
    Nixon, P.D., Passingham, R.E.: Predicting sensory events. The role of the cerebellum in motor learning. Experimental Brain Research 138, 251–257 (2001)Google Scholar
  3. 3.
    Schubotz, R.I., von Cramon, D.Y.: Predicting perceptual events activates corresponding motor schemes in lateral premotor cortex: An fMRI study. NeuroImage 15, 787–796 (2002)CrossRefGoogle Scholar
  4. 4.
    Clark, A., Grush, R.: Towards a Cognitive Robotics. Adaptive Behavior 7, 5–16 (1999)CrossRefGoogle Scholar
  5. 5.
    Parisi, D., Cecconi, F., Nolfi, S.: Econets: Neural networks that learn in an environment. Network 1, 149–168 (1990)CrossRefGoogle Scholar
  6. 6.
    Nolfi, S., Elman, J.L., Parisi, D.: Learning and evolution in neural networks. Adaptive Behavior 3, 5–28 (1994)CrossRefGoogle Scholar
  7. 7.
    Jordan, M.I., Rumelhart, D.E.: Forward models: supervised learning with a distal teacher. Cognitive Science 16, 307–354 (1992)CrossRefGoogle Scholar
  8. 8.
    Sutton, R.S.: Learning to predict by the method of temporal differences. Machine Learning 3, 3–44 (1988)Google Scholar
  9. 9.
    Ackley, D.H., Littman, M.L.: Interactions between learning and evolution. In: Langton, C.G., Taylor, C., Farmer, C.D., Rasmussen, S. (eds.) Artificial Life II, pp. 487–509. Addison-Wesley, Reading (1992)Google Scholar
  10. 10.
    Nolfi, S., Tani, J.: Extracting regularities in space and time through a cascade of prediction networks: The case of a mobile robot navigating in a structured environment. Connection Science 11, 129–152 (1999)CrossRefGoogle Scholar
  11. 11.
    Buss, D.M. (ed.): The Handbook of Evolutionary Psychology. Wiley, New York (2005)Google Scholar
  12. 12.
    Bowlby, J.: Attachment and Loss. Attachment, vol. 1. Hogarth Press, London (1969)Google Scholar
  13. 13.
    Hurford, J.: The evolution of the critical period for language acquisition. Cognition 40, 159–201 (1991)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Daniele Caligiore
    • 1
  • Massimo Tria
    • 1
  • Domenico Parisi
    • 1
  1. 1.Institute of Cognitive Sciences and TechnologiesNational Research CouncilRomeItaly

Personalised recommendations