From NumPy fluency to a served, monitored model in production.
1Python & math foundations
NumPy/pandas fluency plus enough linear algebra and stats to read papers.
0/5 done
2Classical ML
Train, evaluate, and tune models with scikit-learn before reaching for deep learning.
0/5 done
3Deep learning basics
Build and train a model in PyTorch or TensorFlow on a real dataset.
0/5 done
4Data & feature pipelines
Reproducible preprocessing, feature stores, and avoiding train/serve skew.
0/5 done
5Deploy & monitor
Serve a model behind an API, track drift, and set up retraining triggers.
0/5 done