Skip to content

Companion example norm flows #99

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

Open
giovannivolpe wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Companion example norm flows #99

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
82275cf
Create normflows.ipynb
giovannivolpe Jun 28, 2026
5dd33c7
Update normflows.ipynb
giovannivolpe Jun 28, 2026
850bc3f
Update normflows.ipynb
giovannivolpe Jun 28, 2026
5e8b078
Update normflows.ipynb
giovannivolpe Jun 28, 2026
d2328cd
Update normflows.ipynb
giovannivolpe Jun 28, 2026
f26cdfe
Update normflows.ipynb
giovannivolpe Jun 29, 2026
723a365
Update README.md
giovannivolpe Jul 1, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions Companion/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,4 +50,7 @@ CC. **Companion Examples**
> - [**Code Companion PINN: Solving the Heat Equation with a Physics-Informed Neural Network**](https://github.com/DeepTrackAI/DeepLearningCrashCourse/tree/main/Companion/cc_pinn/pinn.ipynb) <a href="https://colab.research.google.com/github/DeepTrackAI/DeepLearningCrashCourse/blob/main/Companion/cc_pinn/pinn.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
> Demonstrates how physical laws can be incorporated directly into the training process of a neural network. The notebook uses automatic differentiation to enforce the heat equation while learning from only a small number of observations, illustrating how PINNs can combine data and domain knowledge to solve differential equations.

> - [**Code Companion NormFlows: Learning Probability Distributions with Normalizing Flows**](https://github.com/DeepTrackAI/DeepLearningCrashCourse/tree/main/Companion/cc_normflows/normflows.ipynb) <a href="https://colab.research.google.com/github/DeepTrackAI/DeepLearningCrashCourse/blob/main/Companion/cc_normflows/normflows.ipynb" target="_parent"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
> Demonstrates how normalizing flows learn complex probability distributions through a sequence of invertible neural-network transformations. The notebook implements a RealNVP model from scratch to transform a simple Gaussian distribution into a two-moons dataset, illustrating exact likelihood training, latent-space representations, and probabilistic generative modeling.

---
Loading