You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The paper can be found here: https://arxiv.org/pdf/2106.10185.pdf
The core idea is to add noise to the weights on each iteration, in proportion to the weights variance in each layer.
It can be added in as an argument in the render() method:
Fast Noisegrad:
The idea is just to add multiplicative noise to the model weights on each optimisation iteration -- but each time to the original model weights. Thus not stacking up any noise.
The paper can be found here: https://arxiv.org/pdf/2106.10185.pdf
The core idea is to add noise to the weights on each iteration, in proportion to the weights variance in each layer.
It can be added in as an argument in the
render()
method:The text was updated successfully, but these errors were encountered: