Adaptive learning rule for binary couplings networks
作者： N. Hendrich
DOI: 10.1109/IJCNN.2000.861530
关键词: Recurrent neural network 、 Wake-sleep algorithm 、 Types of artificial neural networks 、 Computer science 、 Online machine learning 、 Instance-based learning 、 Unsupervised learning 、 Generalization error 、 Learning classifier system 、 Active learning (machine learning) 、 Stability (learning theory) 、 Competitive learning 、 Catastrophic interference 、 Iterative learning control 、 Content-addressable memory 、 Deep learning 、 Leabra 、 Learning rule 、 Theoretical computer science 、 Adaptive learning 、 Artificial neural network 、 Artificial intelligence
摘要: This paper presents a new adaptive iterative learning rule for binary couplings networks. Unlike previous approaches, the algorithm adapts to pattern correlations during and succeeds store highly correlated patterns. Also, by supplying set of default stabilities rule, recall properties network can be adjusted each pattern. Simulations results in simple recursive demonstrate storage associative memory trained show advantage over older rules. Note that adaption step also applied other algorithms. Applications multi-layer networks hardware implementation are discussed.
sci-hub.se 参考文章(10)
Manfred Glesner, Werner Pöchmüller, Neurocomputers: an overview of neural networks in VLSI Chapman and Hall. ,(1994)
N. Hendrich, A scalable architecture for binary couplings attractor neural networks international conference on microelectronics. pp. 213- 220 ,(1996) , 10.1109/MNNFS.1996.493793
E Gardner, B Derrida, Optimal storage properties of neural network models Journal of Physics A. ,vol. 21, pp. 271- 284 ,(1988) , 10.1088/0305-4470/21/1/031
H. K�hler, S. Diederich, W. Kinzel, M. Opper, Learning algorithm for a neural network with binary synapses European Physical Journal B. ,vol. 78, pp. 333- 342 ,(1990) , 10.1007/BF01307854
Werner Krauth, Marc Mézard, Storage capacity of memory networks with binary couplings Journal De Physique. ,vol. 50, pp. 3057- 3066 ,(1989) , 10.1051/JPHYS:0198900500200305700
W Krauth, M Mezard, Learning algorithms with optimal stability in neural networks Journal of Physics A. ,vol. 20, ,(1987) , 10.1088/0305-4470/20/11/013
W Krauth, M Opper, Critical storage capacity of the J = ± 1 neural network Journal of Physics A. ,vol. 22, ,(1989) , 10.1088/0305-4470/22/11/012
L F Abbott, T B Kepler, Optimal learning in neural network memories Journal of Physics A. ,vol. 22, ,(1989) , 10.1088/0305-4470/22/14/011
C J Pérez Vicente, J Carrabina, E Valderrama, Study of a learning algorithm for neural networks with discrete synaptic couplings Network: Computation In Neural Systems. ,vol. 3, pp. 165- 176 ,(1992) , 10.1088/0954-898X_3_2_005
J. J. Hopfield, Neural networks and physical systems with emergent collective computational abilities Proceedings of the National Academy of Sciences of the United States of America. ,vol. 79, pp. 2554- 2558 ,(1982) , 10.1073/PNAS.79.8.2554