Feature/scientific machine learning

[connor-krill]

Scientific Machine Learning

This PR adds the Scientific Machine Learning module to UQpy.

Description

This module uses PyTorch as a backend to preform supervised machine learning. We include a wide range of Layers, network architectures, data-drive losses, divergences, and trainers for neural networks. Alongside the code, there is thorough documentation, examples, and tests to ensure performance, accuracy, and compatibility with PyTorch.

How Has This Been Tested?

We include extensive unit tests for each class introduced. Tests cover a wide range of use cases including for different values and data types. Integration tests are included to ensure smaller classes behave as expected with the larger wrappers and everything is compatible with PyTorch.

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.