Categories › Domain Tracks

Domain Tracks

Focused deep dives on NLP, computer vision, recommendation systems, and time series.

Longer, domain-specific guides that go from the core models to production concerns for one field at a time.

4 posts, from beginner to advanced. Each ends with what to read next.

Domain TracksADVANCED7 min read

Recommendation Systems Engineering: From Collaborative Filtering to Two-Tower Models

How production recommendation systems actually work - collaborative filtering, matrix factorization, two-tower retrieval, learning-to-rank, and the engineering stack that holds it all together.

#retrieval#production-ml#two-tower#recommendation-systems#collaborative-filtering#ranking

Domain TracksINTERMEDIATE5 min read

NLP Engineering: From Text to Production

NLP has transformed with the rise of transformers, but the engineering fundamentals remain: preprocessing, embeddings, fine-tuning, and serving. Here is the full practical stack.

#nlp#transformers#huggingface#deployment

Domain TracksINTERMEDIATE6 min read

Computer Vision Engineering: CNNs, ViTs, and Production

Computer vision went from hand-crafted features to CNNs to Vision Transformers. Understanding all three eras makes you a better practitioner. Here is the practical engineering guide.

#computer-vision#deep-learning#pytorch

Domain TracksINTERMEDIATE6 min read

Time Series ML: Forecasting, Anomaly Detection, and Feature Engineering

Time series data breaks most standard ML assumptions. Here is how to handle temporal dependencies, engineer useful features, build forecasting models, and detect anomalies.

#time-series#python#sklearn