Neural Network Compression: Difference between revisions
m David moved page Neural Network Compression to Private:Neural Network Compression |
m David moved page Private:Neural Network Compression to Neural Network Compression over redirect |
(No difference)
| |
Revision as of 20:36, 2 February 2021
Brief survey on neural network compression techniques.
Pruning
Sensitivity Methods
The idea here is to measure how sensitive each neuron is.
I.e., if you remove the neuron, how will it change the output?
Factorization
Resources
Surveys
- Pruning algorithms a survey (1993) by Russel Reed
- A Survey of Model Compression and Acceleration for Deep Neural Networks (2017) by Cheng et al.