202006091742
Network Pruning
tags: [ neural_networks , src:paper ]
(Blalock et al. 2020Blalock, Davis, Jose Javier Gonzalez Ortiz, Jonathan Frankle, and John Guttag. 2020. “What is the State of Neural Network Pruning?” arXiv.org, March. http://arxiv.org/abs/2003.03033v1.): NN pruning is an iterative method whereby you train a network (or start with a pre-trained model), prune based on assigned scores to structures/parameters, then retrained (since the pruning step will usually reduce accuracy), which is known as fine-tuning.
Backlinks
- [[problems-with-machine-learning-scholarship]]
- Pruning: [[network-pruning]]