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

[WIP] Refactoring NeuralNetwork class #64

Open
wants to merge 17 commits into
base: master
Choose a base branch
from
Open

[WIP] Refactoring NeuralNetwork class #64

wants to merge 17 commits into from

Conversation

singraber
Copy link
Member

  • NeuralNetwork class is the oldest part of the library and not written in modern C++
  • Current implementation only allows single output neuron (not fit for structure detection).
  • New class will use Eigen for all matrix operations.

singraber and others added 16 commits September 6, 2020 00:42
@singraber
Add keyword to select decoupling type.
3dc19d6
@singraber
Fix examples with new keyword.
dce6dd9
@singraber
Added MPI communicator and decoupling group mask
d0a6af3
@singraber
Started with group mask for layer decoupling, WIP!
31bcd58
@singraber
All decoupling group masks look correct
33719c4
@singraber
Introduced new NN weight memory layout
5c540db 
- Weights and biases grouped by neuron.
- Simplifies node decoupling implementation => block submatrices.
- Old weight ordering available via compile flag
(-DALTERNATIVE_WEIGHT_ORDERING)
- Weight file output remains unchanged.
@singraber
Changed decoupling setup
0235ce5 
- Works now with limits instead of a group mask.
- Groups are assumed to be contiguous.
- Implemented rank 0 only update via new communicator.
@singraber
Decoupling on single processor works
0a95ce8
@singraber
Communicate weight segments correctly
11dc116
Merge branch 'master' of github.com:CompPhysVienna/n2p2 into parallel…
9963d14 
…_dekf
@singraber
Add nnp-winit weight initialization test tool
0e57aa8
@singraber
Improved weight modification schemes
6417093 
- Tool nnp-winit also prints also gradients.
@singraber
Merge branch 'parallel_dekf' of github.com:singraber/n2p2 into automa…
ed7c9f2 
…tic-weight-initialization

- Get newest NN functionality here
@singraber
Started refactoring NeuralNetwork class
6506e64
@singraber
Add CI tests for new NN class
b860568
@singraber
Add activation functions, derivatives wrt input
ddb7b2b
@singraber singraber added enhancement New feature or request core Touches the libnnp core library labels Sep 30, 2020
@singraber singraber changed the title Refactoring NeuralNetwork class [WIP] Refactoring NeuralNetwork class Sep 30, 2020
@singraber singraber mentioned this pull request Nov 24, 2020
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
core Touches the libnnp core library enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
1 participant
@singraber