Fast training algorithm for feedforward neural networks: application to crowd estimation at underground stations
作者： T.W.S. Chow , J.Y.-F. Yam , S.-Y Cho
DOI: 10.1016/S0954-1810(99)00016-3
关键词:
摘要: Abstract A hybrid fast training algorithm for feedforward networks is proposed. In this algorithm, the weights connecting last hidden and output layers are firstly evaluated by least-squares whereas between input using modified gradient descent algorithms. The effectiveness of proposed demonstrated applying it to sunspot Mackey–Glass time-series prediction. results showed that can greatly reduce number flops required train networks. also applied crowd estimation at underground stations very promising obtained.
elsevier.com
sci-hub.se 参考文章(14)
Christopher M. Bishop, Neural networks for pattern recognition ,(1995)
Carlo S Regazzoni, Alessandra Tesei, Vittorio Murino, None, A real-time vision system for crowding monitoring conference of the industrial electronics society. pp. 1860- 1864 ,(1993) , 10.1109/IECON.1993.339357
Y.F. Yam, T.W.S. Chow, Extended backpropagation algorithm Electronics Letters. ,vol. 29, pp. 1701- 1702 ,(1993) , 10.1049/EL:19931131
Y. F. Yam, Tommy W. S. Chow, Accelerated training algorithm for feedforward neural networks based on least squares method Neural Processing Letters. ,vol. 2, pp. 20- 25 ,(1995) , 10.1007/BF02279934
T.W.S. Chow, C.-T. Leung, Nonlinear autoregressive integrated neural network model for short-term load forecasting IEE Proceedings - Generation, Transmission and Distribution. ,vol. 143, pp. 500- 506 ,(1996) , 10.1049/IP-GTD:19960600
Friedrich Biegler-König, Frank Bärmann, Original Contribution: A learning algorithm for multilayered neural networks based on linear least squares problems Neural Networks. ,vol. 6, pp. 127- 131 ,(1993) , 10.1016/S0893-6080(05)80077-2
M. Mackey, L Glass, Oscillation and chaos in physiological control systems Science. ,vol. 197, pp. 287- 289 ,(1977) , 10.1126/SCIENCE.267326
S. Ergezinger, E. Thomsen, An accelerated learning algorithm for multilayer perceptrons: optimization layer by layer IEEE Transactions on Neural Networks. ,vol. 6, pp. 31- 42 ,(1995) , 10.1109/72.363452
A.C. Davies, S.A. Velastin, Jia Hong Yin, Crowd monitoring using image processing Electronics & Communication Engineering Journal. ,vol. 7, pp. 37- 47 ,(1995) , 10.1049/ECEJ:19950106
M.T. Hagan, M.B. Menhaj, Training feedforward networks with the Marquardt algorithm IEEE Transactions on Neural Networks. ,vol. 5, pp. 989- 993 ,(1994) , 10.1109/72.329697