Learning, invariance, and generalization in high-order neural networks
作者： C. Lee Giles , Tom Maxwell
DOI: 10.1364/AO.26.004972
关键词: Stochastic neural network 、 Optics 、 Artificial intelligence 、 Content-addressable memory 、 Types of artificial neural networks 、 Computer science 、 Artificial neural network 、 Catastrophic interference 、 Nervous system network models 、 Time delay neural network 、 Cellular neural network 、 Deep learning
摘要: High-order neural networks have been shown to impressive computational, storage, and learning capabilities. This performance is because the order or structure of a high-order network can be tailored problem. Thus, designed for particular class problems becomes specialized but also very efficient in solving those problems. Furthermore, priori knowledge, such as geometric invariances, encoded networks. Because this knowledge does not learned, these are that utilize knowledge.
osapublishing.org
elsevier.com
harvard.edu参考文章(15)
Geoffrey F. Hinton, A parallel computation that assigns canonical object-based frames of reference international joint conference on artificial intelligence. pp. 683- 685 ,(1981)
T. Maxwell, C. L. Giles, Y. C. Lee, H. H. Chen, Nonlinear dynamics of artificial neural systems Neural Networks for Computing. ,vol. 151, pp. 299- 304 ,(2008) , 10.1063/1.36227
Terrence J. Sejnowski, Higher‐order Boltzmann machines AIP Conference Proceedings 151, Neural Networks for Computimg. ,vol. 151, pp. 398- 403 ,(2008) , 10.1063/1.36246
Y C Lee, H H Chen, C L Giles, T Maxwell, H Y Lee, G Z Sun, High order correlation model for associative memory AIP Conference Proceedings 151 on Neural Networks for Computing. pp. 86- 99 ,(1987)
S. Grossberg, Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors Biological Cybernetics. ,vol. 23, pp. 121- 134 ,(1976) , 10.1007/BF00344744
Y.C. Lee, Gary Doolen, H.H. Chen, G.Z. Sun, Tom Maxwell, H.Y. Lee, C. Lee Giles, Machine learning using a higher order correlation network Physica D: Nonlinear Phenomena. ,vol. 2, pp. 276- 306 ,(1986) , 10.1016/0167-2789(86)90300-6
Y. Owechko, G. J. Dunning, E. Marom, B. H. Soffer, Holographic associative memory with nonlinearities in the correlation domain Applied Optics. ,vol. 26, pp. 1900- 1910 ,(1987) , 10.1364/AO.26.001900
D. Psaltis, J. Hong, S. Venkatesh, John A. Neff, Shift Invariance In Optical Associative Memories O-E/LASE'86 Symp (January 1986, Los Angeles). ,vol. 0625, pp. 189- 195 ,(1986) , 10.1117/12.963498
P. Peretto, J. J. Niez, Long term memory storage capacity of multiconnected neural networks Biological Cybernetics. ,vol. 54, pp. 53- 64 ,(1986) , 10.1007/BF00337115
Dana Angluin, Carl H. Smith, Inductive Inference: Theory and Methods ACM Computing Surveys. ,vol. 15, pp. 237- 269 ,(1983) , 10.1145/356914.356918