Development - SciML

[connor-krill]

Scientific Machine Learning

Adds the Scientific Machine Learning module for neural networks defined with PyTorch

Description

Introduces objects for Bayesian neural networks and neural operators in PyTorch. The new features include Bayesian counterparts to common neural network layers, deterministic and Bayesian Fourier layers, and divergence formulas used to train Bayesian neural networks.

How Has This Been Tested?

All new methods have been extensively tested and type hinted for accuracy and ease of use. The test cover a wide range of use cases, inputs, and check that features raise the appropriate error when misused.

Types of changes

What types of changes does your code introduce? Put an x in all the boxes that apply:

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to change)

Checklist:

Go over all the following points, and put an x in all the boxes that apply.
If you're unsure about any of these, don't hesitate to ask. We're here to help!

• My code follows the code style of this project.
• My change requires a change to the documentation.
• I have updated the documentation accordingly.
• I have read the CONTRIBUTING document.
• I have added tests to cover my changes.
• All new and existing tests passed.

[connor-krill]

Reopening to run SonarCloud and tests

[sonarqubecloud]

Quality Gate passed

Issues
0 New issues
27 Accepted issues

Measures
0 Security Hotspots
95.1% Coverage on New Code
3.0% Duplication on New Code

See analysis details on SonarQube Cloud