跳转至

Backpropagation

Papers

1986-Learning representations by back-propagating errors

Learning representations by back-propagating errors1. 通过 BP 进行梯度下降更新来训练 NN 的开山之作。

2023-The Backpropagation algorithm for a math student

The Backpropagation algorithm for a math student2. 文章通过 Jacobian Matrix 来阐述反向传播中梯度的计算和更新,这种方法相比直接从矩阵/向量求导入手更加容易理解。 此外论文从简单到复杂,一步步的推导过程让论文理解起来更加容易。


  1. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, “Learning representations by back-propagating errors,” nature, vol. 323, no. 6088, pp. 533–536, 1986. 

  2. S. Damadi, G. Moharrer, M. Cham, and J. Shen, “The backpropagation algorithm for a math student,” in 2023 international joint conference on neural networks (IJCNN), IEEE, 2023, pp. 01–09.