摘要: This paper shows how a representation at multiple scales can be used for generalization in instrumental learning. The use of such representations is an efficient way to code similarities and differences within stimulus dimension, allows learning system generalize easily between various situations. A neural network based model classical conditioning presented its ability using multi-scale subsequently demonstrated number simulations.
researchgate.net 参考文章(14)
Robert A Rescorla, None, A theory of Pavlovian conditioning : Variations in the effectiveness of reinforcement and nonreinforcement Classical conditioning II : Current research and theory. pp. 64- 99 ,(1972)
Christian Balkenius, Some properties of neural representations selected papers from the Swedish conference on Connectionism in a broad perspective. pp. 79- 88 ,(1994)
B. WIDROW, M. E. HOFF, Adaptive switching circuits Neurocomputing: foundations of research. pp. 123- 134 ,(1988) , 10.21236/AD0241531
Jeffrey Alan Gray, Elements of a two-process theory of learning ,(1975)
Stephen Kitzis, Stephen Grossberg, The Adaptive Brain American Journal of Psychology. ,vol. 103, pp. 426- ,(1990) , 10.2307/1423222
A. Harry Klopf, Scott E. Weaver, James S. Morgan, A hierarchical network of control systems that learn: modeling nervous system function during classical and instrumental conditioning Adaptive Behavior. ,vol. 1, pp. 263- 319 ,(1993) , 10.1177/105971239300100302
C. L. Hull, The goal-gradient hypothesis and maze learning. Psychological Review. ,vol. 39, pp. 25- 43 ,(1932) , 10.1037/H0072640
Nicholas Mackintosh, The psychology of animal learning ,(1974)
Nicholas Mackintosh, Conditioning and associative learning ,(1983)
Andrew P. Witkin, Scale-space filtering international joint conference on artificial intelligence. pp. 329- 332 ,(1987) , 10.1016/B978-0-08-051581-6.50036-2