A Collection of 25 Awesome Python Scripts (mini projects)
#Python

Announcing "Lineax" - newest #JAX library! For fast linear solves and least squares.

GitHub: github.com/google/lineax

* Fast compile time
* Fast runtime
* Efficient new algorithms (e.g. QR) + existing ones (GMRES, LU, SVD, ...)
* Support for general linear operators🔥

Link to the Videos of the course added.

The courses of high performance computation from CSCS are highly recommended.

YouTube

plt.rc is a Matplotlib function that can be used to modify the runtime configuration (rc) settings of a plot. The rc settings control the defaults of almost every property in Matplotlib, such as figure size and DPI, line width, font size, and color

link

#snippet
Kuramoto order parameter (KOP)
extract phase from given time series using hilbert transform and calculate the KOP.

Elicit.org
The AI Research Assistant

COMPUTATIONAL PSYCHIATRY COURSE ZURICH
This course is organized by the Translational Neuromodeling Unit (TNU), University of Zurich & ETH Zurich and is designed to provide MSc and PhD students, scientists clinicians and anyone interested in Computational Psychiatry with the necessary toolkit to master challenges in computational psychiatry research.

Pre-requisites: Some background knowledge in neuroscience, neuroimaging, (Bayesian) statistics & probability theory, programming and machine learning is expected. If you lack this background, it is recommended that you prepare for this course.

https://www.translationalneuromodeling.org/cpcourse/

Preparation Resources
Lectures
Lecture Recordings
Tutorials
Reading List

ISLR with applications in Python is out! 🚀🚀🚀

An Introduction to Statistical Learning (ISLR), by Profs James, Witten, Hastie, and Tibshirani, in my opinion, is one of the best introductory books for machine learning ❤️. The book focuses on the foundations of data science and originally was with R examples. Today, the authors, along with Prof. Taylor, released a Python edition for the 2nd version of the book. The book covers topics such as:
✅ Regression and classification
✅ Linear model selection and regularization
✅ Non-linear regression
✅ Tree-based methods
✅ Support vector machines
✅ Deep learning
✅ Unsupervised learning

Both the R and Python versions of the book are available for free

R version
Python version

Have fun learning!👌

One can put this at the beginning of the notebook to check the packages in active environment.
given "d" is suggested package versions.

Python file

Deep Learning with JAX

Notebooks for the chapters:
1. Intro to JAX
- JAX Speedup
2. Your first program in JAX
- MNIST image classification with MLP in pure JAX
3. Working with tensors
- Image Processing with Tensors
- Working with DeviceArray's
4. Autodiff
- Different ways of getting derivatives
- Working with gradients in TensorFlow, PyTorch, and JAX
- Differentiating in JAX
5. Compiling your code
- JIT compilation and more: JIT, Jaxpr, XLA, AOT
6. Vectorizing your code
- Different ways to vectorize a function, Controlling vmap() behavior, More real-life cases
7. Parallelizing your computations
- Using pmap()
8. Advanced parallelization
- Using xmap()
- Using pjit()
- Tensor sharding
- Multi-host example
9. Random numbers in JAX
- Random augmentations, NumPy and JAX PRNGs
9. Complex structures in JAX/Pytrees
- Pytrees, jax.tree_util functions, custom nodes
11. more to come

Github

How To Build a Neural Network to Recognize
Handwritten Digits with TensorFlow


- measuring loss per epoch
- adding dropout probability
- adding callback function to automatically abort the training based on a condition on changing loss value per epoch.


GitHub notebook

Ops..., it's public now.

Machine Learning refresher.