By analyzing and comparing the characteristics of neural network models and complex systems and the requirements of their modeling methodology, it is shown that the applications of the neural network in the complex system modeling are feasible. The main application fields of the neural network in the complex system modeling are discussed, such as the natural language processing, the speech recognition, the visual processing, and the fault diagnosis; and the main problems are pointed out, including the facts that the neural network can not describe the structure and the evolution of the system, it can not handle multiple tasks at the same time, and it can not solve the non repetitive problems well. Also the solutions of these problems are discussed preliminarily.
ZHANG Guoning
,
HUANG Xiangyuan
. Applications of neural network in complex system modeling[J]. Science & Technology Review, 2018
, 36(12)
: 66
-70
.
DOI: 10.3981/j.issn.1000-7857.2018.12.009
[1] Hinton G, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786):504-507.
[2] Vos N, Meijden H, Denessen E. Effects of constructing versus playing an educational game on student motivation and deep learning strategy use[J]. Computers & Education, 2011, 56(1):127-137.
[3] McCulloch W, Pitts W. A logical calculus of the ideas imma-nent in nervous activity[J]. Bulletin of Mathematical Biophys-ics, 1943, 5(4):115-133.
[4] Rosenblatt F. The perceptron:A probabilistic model for infor-mation storage and organization in the brain[J]. Psychological Review, 1958, 65(6):386-408.
[5] Minsky M, Paypert S. Perceptrons[M]. Cambridge:MIT Press, 1969.
[6] Hopfield J. Neural networks and physical systems with emer-gent collective computational abilities[J]. Proceedings of the National Academy of Sciences of the United States of America, 1982, 79(8):2554-2558.
[7] Ackley D, Hinton G, Sejnowski T J. A learning algorithm for Boltzmann machines[J]. Cognitive Science, 1985, 9:147-169.
[8] Hinton G, Osindero S, Teh Y. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18:1527-1554.
[9] Rumelhart D, Hinton G, Williams R. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.
[10] Fukushima K. Neocognitron:A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics, 1980, 36:193-202.
[11] LeCun Y, Bottou L, Bengio Y, et al. Gradient based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[12] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780.
[13] Silver D, Huang A, Maddison C, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529(7587):484-489.
[14] Tan T, Qian Y, Yin M, et al. Cluster adaptive training for deep neural network[C]//International Conference on Acous-tics, Speech and Signal Processing. South Brisbane, Queensland, Australia:IEEE, 2015:4325-4329.
[15] Yu Z, Wang H X, Lin X M, et al. Understanding short texts through semantic enrichment and hashing[J]. IEEE Transac-tions on Knowledge and Data Engineering, 2016, 28(2):566-579.
[16] Hu W P, Qian Y, Soong F K, et al. Improved mispronuncia-tion detection with deep neural network trained acoustic mod-els and transfer learning based logistic regression classifiers[J]. Speech Communication, 2015, 67:154-166.
[17] Seide F, Li G, Yu D. Conversational speech transcription us-ing context-dependent deep neural networks[C]//Proceedings of the Annual Conference of the International Speech Commu-nication Association. Nes York:Curran Associates, 2011:437-440.
[18] Schroff F, Kalenichenko D, Philbin J. FaceNet:A unified em-bedding for face recognition and clustering[C]//IEEE Confer-ence on Computer Vision and Pattern Recognition. IEEE Computer Society, 2015:815-823.
[19] Sun W J, Shao S Y, Zhao R, et a1. A sparse auto-encoderbased deep neural network approach for induction motor faults classification[J]. Measurement, 2016, 89:171-178.
[20] Sabour S, Hinton G. Dynamic routing between capsules[EB/OL].[2018-03-06]. http://arxiv.org/pdf/1710.09829v1.pdf.
