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

Implement complex layers #3

Closed
7 tasks done
romech opened this issue Jan 7, 2021 · 2 comments
Closed
7 tasks done

Implement complex layers #3

romech opened this issue Jan 7, 2021 · 2 comments
Assignees
@bwconrad
Milestone
Week 1-2

Comments

@romech
Copy link
Owner

romech commented Jan 7, 2021 •
edited by bwconrad

  • Convolutions
  • ReLU
  • Batch norm
  • Avg/Max pooling
  • Dropout
  • Skip-connections

Additionally:

  • Noise+Rotation function f(a, b, θ) = exp(iθ)[a+bi]

Implementer would need to decide whether tensors should be (Re, Im) or (r, φ). I think the latter is better.

Also, having a couple of unit tests would be nice.
@romech romech added this to the Week 1-2 milestone Jan 7, 2021
@bwconrad
Copy link
Collaborator

bwconrad commented Jan 7, 2021

I can do this.

@bwconrad bwconrad self-assigned this Jan 7, 2021
This was referenced Jan 7, 2021
Closed
Merged
@bwconrad
Copy link
Collaborator

This is done for now. It their are issues with these when we implement the whole complex network then a new issue can be opened.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@bwconrad bwconrad

Labels
None yet
Projects
None yet
Milestone
Week 1-2
Development

No branches or pull requests
2 participants
@romech @bwconrad