1. Y. LeCun, J. S. Denker, and S. A. Solla, “Optimal brain damage.” 598–605.
2. B. Hassibi, and D. G. Stork, “Second order derivatives for network pruning: Optimal brain surgeon.” 164–171.
3. Pruning filters for efficient convnets;Li,2016
4. The lottery ticket hypothesis: Finding sparse, trainable neural networks;Frankle,2018
5. S. J. Hanson, and L. Y. Pratt, “Comparing biases for minimal network construction with back-propagation.” 177–185.