Abstract
The performance of the extended Bush-Mosteller learning and imprinting scheme developed previously is studied for stationary and non-stationary stochastic environments. As a performance criterion the average missing information level is chosen. For a stationary environment the approximate time course of the latter is derived and discussed, an exact symmetry in the performance of learning and imprinting schemes is proved, and the biological advantage of imprinting processes, with respect to energy consumption, is pointed out. For a non-stationary environment the performance of proper learning schemes is shown to be superior to imprinting processes, as the adaptability of the latter to novel environmental properties decreases exponentially in time. The optimal memory range of a learning system is calculated as a function of the time span during which the environment changes significantly and of the mean amplitude with which these changes occur.
Similar content being viewed by others
References
Atkinson,R.C., Bower,G.H., Crothers,E.J.: An introduction to mathematical learning theory. New York: Wiley 1965
Bush,R.R., Mosteller. F.: Psychol. Rev. 58, 313 (1951)
Bush,R.R., Mosteller,F.: Ann. Math. Stat. 24, 559 (1953)
Bush,R.R., Mosteller,F.: Stochastic models for learning. New York: Wiley 1955
Feichtinger,G.: Metrika 18, 35 (1971)
Fisz,M.: Wahrscheinlichkeitsrechnung und mathematische Statistik. Berlin: VEB Deutscher Verlag der Wissenschaften. 1971
Kullback,S.: Information theory and statistics. New York: Dover 1968
Pfaffelhuber,E.: Intern. J. Neuroscience3, 83 (1972); and in: M. Conrad and M.E. Magar (Eds.): Physical principles of neuronal and organismic behavior. London: Gordon and Breach 1973
Pfaffelhuber,E.: A model for learning and imprinting with finite and infinite memory range. Kybernetik 12, 229–236 (1973a)
Pfaffelhuber,E.: Approximate source probabilities, relative entropy, and realistic high probability groups. Proc. IEEE Intern. Symp. Information Theory, Israel 1973b
Pfaffelhuber,E.: Minimax information gain and maximum entropy principle. Preprint. University of Tübingen 1973c
Pfaffelhuber,E.: Mathematical learning models and neuronal networks. J. theor. Biol. 1973d (in press)
Pfaffelhuber,E., Damle, P.S.: Mathematical learning models and neural networks. Proc. Trieste Neural Network Meeting 1972
Pfaffelhuber,E., Damle, P.S.: Mathematical learning models and modifiable synapses. Intern. J. Neuroscience (in press) 1973
Watanabe,S.: Knowing and guessing. New York: Wiley 1969
Author information
Authors and Affiliations
Additional information
Supported by the Deutsche Forschungsgemeinschaft and the Humboldt Foundation.
Fellow of the Humboldt Foundation; on leave of absence from the University of Poona, India.
Rights and permissions
About this article
Cite this article
Pfaffelhuber, E., Damle, P.S. Learning and imprinting in stationary and non-stationary environment. Kybernetik 13, 229–237 (1973). https://doi.org/10.1007/BF00274888
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00274888