Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Use weight initialisations from Flux.jl #76

Closed
nic-barbara opened this issue May 29, 2023 · 0 comments · Fixed by #103
Closed

Use weight initialisations from Flux.jl #76

nic-barbara opened this issue May 29, 2023 · 0 comments · Fixed by #103
Labels
enhancement New feature or request

Comments

@nic-barbara
Copy link
Member

We currently use a custom glorot_normal function to initialise all the weights in the RENs. Instead, we should use any of the built-in initialisation functions with Flux.jl (eg: Flux.glorot_normal or Flux.glorot_uniform) and allow the user to choose when constructing DirectRENParams. This is similar to how DirectLBDNParams works currently.
@nic-barbara nic-barbara added the enhancement New feature or request label Jun 9, 2023
@nic-barbara nic-barbara linked a pull request Jul 13, 2023 that will close this issue
Feature/rand init #103
Merged
@nic-barbara nic-barbara removed a link to a pull request Jul 13, 2023
Feature/rand init #103
Merged
@nic-barbara nic-barbara linked a pull request Jul 13, 2023 that will close this issue
Feature/rand init #103
Merged
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Feature/rand init acfr/RobustNeuralNetworks.jl
1 participant
@nic-barbara