Instructor since 2023
Fatima Idrissi
Machine learning engineer teaching scikit-learn, PyTorch and modern NLP from the ground up
Sample
- Students
- 7,660
- Courses
- 3
- Instructor rating
- 4.4
- Reviews
- 21
About Fatima
I build and evaluate machine learning models, mostly for text and tabular data. My work covers the whole loop: preparing data, training baselines, trying deep learning when it is worth it, and measuring whether the model actually helps.
In my courses I start with the simplest model that could work and only add complexity when the numbers justify it. You will write the training loop yourself before using higher level tools, so nothing feels like magic.
I also enjoy reading papers and turning the useful parts into small, runnable notebooks.
Courses by Fatima
What students say
Laila T.
Sample Model cards lesson was a nice touch
We now write a model card for every model we ship, and it has helped reviews a lot.
Jin W.
Sample Shapes, shapes, shapes
The habit of printing shapes after every step fixed most of my early bugs. Great teaching.
Nadia R.
Sample Baseline first was humbling
Our TF-IDF baseline was only three points behind the transformer. That changed our whole project plan.
Ingrid S.
Sample Honest about what models can do
The fairness and interpretation lessons were thoughtful and practical, not preachy.
Benjamin F.
Sample The training loop finally makes sense
Writing the loop by hand and then breaking it on purpose taught me more than any high level API.
Victoria H.
Sample Leakage lesson saved my project
I had been scaling before splitting for months. The pipeline approach fixed my overly optimistic results.
Erik J.
Sample LoRA section is excellent
Clear explanation and working code. We now serve four tasks from one base model with adapters.
Aiko N.
Sample Excellent transfer learning section
Fine tuning ResNet on a small plant dataset gave great results with very little data.