Symbolic-neural systems and the use of hints for developing complex systems
作者： Steven C. Suddarth , Alistair D.C. Holden
DOI: 10.1016/S0020-7373(05)80130-0
关键词: Content-addressable memory 、 Artificial intelligence 、 Monotonic function 、 Entropy (order and disorder) 、 Entropy (arrow of time) 、 Entropy (energy dispersal) 、 Entropy (statistical thermodynamics) 、 Artificial neural network 、 Entropy (information theory) 、 Complex system 、 Entropy (classical thermodynamics) 、 Neural system 、 Computer science
摘要: Neural network systems can be made to learn faster and generalize better through the addition of knowledge. Two methods are investigated for adding this knowledge: (1) decomposition networks; (2) rule-injection hints. Both these approaches play a role similar rules or defining algorithms in symbolic systems. Analyses explain two important points: what functions which easy (as well as make effective hints) known from an analysis effect learning monotonic functions; set theory functional entropy shows kinds hints useful. The have been tested variety settings, example application using lunar lander game is discussed.
elsevier.com
sci-hub.se 参考文章(10)
R. J. Williams, The logic of activation functions Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. pp. 423- 443 ,(1986)
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams, Learning representations by back-propagating errors Nature. ,vol. 323, pp. 696- 699 ,(1988) , 10.1038/323533A0
S. C. Suddarth, Y. L. Kergosien, Rule-Injection Hints as a Means of Improving Network Performance and Learning Time Lecture Notes in Computer Science. ,vol. 412, pp. 120- 129 ,(1990) , 10.1007/3-540-52255-7_33
Suddarth, Sutton, Holden, A symbolic-neural method for solving control problems IEEE 1988 International Conference on Neural Networks. pp. 516- 523 ,(1988) , 10.1109/ICNN.1988.23886
Richard S. Sutton, Andrew G. Barto, Toward a modern theory of adaptive networks: Expectation and prediction. Psychological Review. ,vol. 88, pp. 135- 170 ,(1981) , 10.1037/0033-295X.88.2.135
J.A. Feldman, D.H. Ballard, Connectionist models and their properties Cognitive Science. ,vol. 6, pp. 205- 254 ,(1982) , 10.1207/S15516709COG0603_1
Suddarth, Bourrely, A back-propagation associative memory for both positive and negative learning international joint conference on neural network. pp. 612- ,(1989) , 10.1109/IJCNN.1989.118448
Ryszard S. Michalski, Pattern Recognition as Rule-Guided Inductive Inference IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 2, pp. 349- 361 ,(1980) , 10.1109/TPAMI.1980.4767034
David S. Touretzky, Geoffrey E. Hinton, A Distributed Connectionist Production System Cognitive Science. ,vol. 12, pp. 423- 466 ,(1988) , 10.1207/S15516709COG1203_4
D. E. Rumelhart, G. E. Hinton, R. J. Williams, Learning internal representations by error propagation Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. ,vol. 1, pp. 318- 362 ,(1986)