Some Adaptive Advantages of the Ability to Make Predictions
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.
KeywordsSensory Input Current Input Connection Weight Output Unit Average Fitness
Unable to display preview. Download preview PDF.
- 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
- 8.Sutton, R.S.: Learning to predict by the method of temporal differences. Machine Learning 3, 3–44 (1988)Google Scholar
- 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
- 11.Buss, D.M. (ed.): The Handbook of Evolutionary Psychology. Wiley, New York (2005)Google Scholar
- 12.Bowlby, J.: Attachment and Loss. Attachment, vol. 1. Hogarth Press, London (1969)Google Scholar