Fix Minibatch alignment in Bayesian Neural Network example

[Deepakchowdavarapu]

Fix Minibatch Alignment in Bayesian Neural Network Example

• Notebook follows style guide https://docs.pymc.io/en/latest/contributing/jupyter_style.html
• PR description contains a link to the relevant issue:
  • Fixes issue Bug in "Variational Inference: Bayesian Neural Networks" notebook #654
• Check the notebook is not excluded from any pre-commit check: https://github.com/pymc-devs/pymc-examples/blob/main/.pre-commit-config.yaml

Issue

Fixes #654.

Description

This PR addresses the issue where Minibatch variables for X_train and Y_train were created separately, causing potential misalignment in slices and thus random pairing of X with unrelated y.

Changes Made

• Updated the code to create a single Minibatch for X_train and Y_train together, ensuring identical slices.
• Modified the construction of ann_input and ann_output using the unified Minibatch variables.
• Removed redundant parameters from the construct_nn function.
• Confirmed model architecture and initialization remain consistent.

Impact

This change ensures that the model training process is more robust and prevents issues related to incorrect data alignment in minibatches.

Helpful links

• https://github.com/pymc-devs/pymc-examples/blob/main/CONTRIBUTING.md

---

📚 Documentation preview 📚: https://pymc-examples--689.org.readthedocs.build/en/689/

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[Deepakchowdavarapu]

@yoshida-chem @twiecki please review waiting for your response

[twiecki]

Thanks @Deepakchowdavarapu! You need to run pre-commit locally so that the myst file is generated.

[Deepakchowdavarapu]

@twiecki ok sure can you please assign this issue to me !!!

[twiecki]

There's no issue, on this PR you'd need to run pre-commit run --all-files and then commit and push.

[Deepakchowdavarapu]

pre-commit.ci autofix

[twiecki]

We might not have set that up here, but we should. Is pre-commit giving you problems?

[Deepakchowdavarapu]

I will run it locally and raise a new PR soon.