Skip to content

Commit

Permalink
chore: remove footnotes in doc (#1662)
Browse files Browse the repository at this point in the history
  • Loading branch information
andrei-stoian-zama authored Sep 5, 2022
1 parent 393510e commit 186f888
Showing 1 changed file with 1 addition and 3 deletions.
4 changes: 1 addition & 3 deletions docs/advanced-topics/pruning.md
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,4 @@ Fixing some of the weights to 0 makes the network graph look more similar to the

![Pruned Fully Connected Neural Network](../figures/prunednet.png)

While pruning weights can reduce the prediction performance of the neural network, studies show that a high level of pruning (above 50% \[^1\]) can often be applied. See here how Concrete-ML uses pruning in [Fully Connected Neural Networks](../_apidoc/concrete.ml.sklearn.html#concrete.ml.sklearn.qnn.NeuralNetClassifier).

\[^1\]: Han, Song & Pool, Jeff & Tran, John & Dally, William. (2015). Learning both Weights and Connections for Efficient Neural Networks.
While pruning weights can reduce the prediction performance of the neural network, studies show that a high level of pruning (above 50%) can often be applied. See here how Concrete-ML uses pruning in [Fully Connected Neural Networks](../_apidoc/concrete.ml.sklearn.html#concrete.ml.sklearn.qnn.NeuralNetClassifier).

0 comments on commit 186f888

Please sign in to comment.