5,351
edits
Neural Network Compression: Difference between revisions
→Sensitivity Methods
m (David moved page Private:Neural Network Compression to Neural Network Compression over redirect) |
|||
| Line 5: | Line 5: | ||
The idea here is to measure how sensitive each neuron is. | The idea here is to measure how sensitive each neuron is. | ||
I.e., if you remove the neuron, how will it change the output? | I.e., if you remove the neuron, how will it change the output? | ||
* 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. | |||
==Factorization== | ==Factorization== | ||