论文信息 - Backpropagation method modification using Taylor series to improve accuracy of offline neural network training - 字舞流文

Backpropagation method modification using Taylor series to improve accuracy of offline neural network training

A. I. Glushchenko | Vladislav A. Petrov | Konstantin A. Lastochkin

[1] Yoram Singer,et al. Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[2] Jimmy Ba,et al. Adam: A Method for Stochastic Optimization , 2014, ICLR.

[3] Sebastian Ruder,et al. An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[4] Quoc V. Le,et al. On optimization methods for deep learning , 2011, ICML.

[5] Jorge Nocedal,et al. On the limited memory BFGS method for large scale optimization , 1989, Math. Program..

[6] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[7] Ken-ichi Funahashi,et al. On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[8] Hao Yu,et al. Levenberg—Marquardt Training , 2011 .