5,351
edits
Neural Network Compression: Difference between revisions
→Pruning
No edit summary |
|||
| Line 7: | Line 7: | ||
* Mozer and Smolensky (1988)<ref name="mozer1988skeletonization"></ref> use a gate for each neuron. Then the sensitivity and be estimated with the derivative w.r.t the gate. | * Mozer and Smolensky (1988)<ref name="mozer1988skeletonization"></ref> use a gate for each neuron. Then the sensitivity and be estimated with the derivative w.r.t the gate. | ||
* Karnin estimates the sensitivity by monitoring the change in weight during training. | |||
==Factorization== | ==Factorization== | ||