Network Dynamics Governed by Lyapunov Functions: From Memory to Classification.
作者： Merav Stern , Eric Shea-Brown
DOI: 10.1016/J.TINS.2020.04.002
关键词: Artificial intelligence 、 Network dynamics 、 Artificial neural network 、 Computational neuroscience 、 Lyapunov function 、 Learning rule 、 Computer science
摘要: In 1982, John Hopfield published a neural network model for memory retrieval, that became cornerstone in theoretical neuroscience. recent paper, Krotov and built on these early studies showed how incorporates biologically plausible learning rule governed by Lyapunov function can effectively perform classification tasks.
arxiv.org
harvard.edu
sci-hub.st 参考文章(11)
Yoshua Bengio, Dong-Hyun Lee, Saizheng Zhang, Asja Fischer, Difference target propagation european conference on machine learning. pp. 498- 515 ,(2015) , 10.1007/978-3-319-23528-8_31
Warren S. McCulloch, Walter Pitts, A logical calculus of the ideas immanent in nervous activity Bulletin of Mathematical Biology. ,vol. 52, pp. 99- 115 ,(1990) , 10.1007/BF02478259
Cengiz Pehlevan, Dmitri B. Chklovskii, A Hebbian/Anti-Hebbian network derived from online non-negative matrix factorization can cluster and discover sparse features 2014 48th Asilomar Conference on Signals, Systems and Computers. pp. 769- 775 ,(2014) , 10.1109/ACSSC.2014.7094553
Donald O. Hebb, The Organization of Behavior: A Neuropsychological Theory ,(1949)
Michael A. Cohen, Stephen Grossberg, Absolute stability of global pattern formation and parallel memory storage by competitive neural networks systems man and cybernetics. ,vol. 42, pp. 815- 826 ,(1983) , 10.1109/TSMC.1983.6313075
Daniel J. Amit, Hanoch Gutfreund, H. Sompolinsky, Storing infinite numbers of patterns in a spin-glass model of neural networks. Physical Review Letters. ,vol. 55, pp. 1530- 1533 ,(1985) , 10.1103/PHYSREVLETT.55.1530
J. J. Hopfield, Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences of the United States of America. ,vol. 81, pp. 3088- 3092 ,(1984) , 10.1073/PNAS.81.10.3088
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
Erkki Oja, Simplified neuron model as a principal component analyzer Journal of Mathematical Biology. ,vol. 15, pp. 267- 273 ,(1982) , 10.1007/BF00275687
Timothy P. Lillicrap, Daniel Cownden, Douglas B. Tweed, Colin J. Akerman, Random synaptic feedback weights support error backpropagation for deep learning. Nature Communications. ,vol. 7, pp. 13276- 13276 ,(2016) , 10.1038/NCOMMS13276