BeginnerTrain your first machine learning model in 20 lines of Python
No maths degree required. Load data, split it, fit a model, check the score — the four steps every scikit-learn project uses, explained line by line.
Machine Learning
From your first scikit-learn model to writing a transformer by hand. The fundamentals, the internals, and the evaluation mistakes that make good numbers meaningless.
Fundamentals
Train a model, split your data properly, and understand what the numbers are telling you.
Deep Learning
Attention, transformers, convolutions and embeddings — worked out with real numbers instead of hand-waving.
AdvancedEmbeddings mathematically: what cosine similarity measures
The geometry of embedding space: why you normalise, what dimensionality really buys you, and the anisotropy problem nobody mentions.
AdvancedThe attention mechanism, worked out by hand
Queries, keys and values with real numbers. Why the scaling factor is sqrt(d_k), what multi-head attention buys, and how causal masking works.
AdvancedTransformer from scratch in PyTorch, block by block
A working decoder-only transformer in 120 lines. Pre-norm, residual streams, why the MLP is 4x wide, weight tying, stable initialisation.
Evaluation & Production
Measuring models honestly, finding the leaks that survive a correct split, and keeping them working after deployment.
AdvancedML model evaluation mistakes that make good numbers meaningless
Nine errors behind great offline metrics and bad production models: random splits on time series, threshold-free metrics, tuning on the test set.
AdvancedData leakage: the kinds that survive your train/test split
Splitting correctly stops the obvious leak. Target encoding, feature stores, label windows and proxy features leak anyway — how to find each.
AdvancedProduction ML architecture: training-serving skew
The model is the small part. Training-serving skew, feature freshness, shadow deploys, drift detection, and monitoring that catches decay.
Newsletter
Get new articles
Free essays on learning, Python, and ML — no account required. We’ll only email when there’s something worth reading.