Read
Short, practical reads on AI and data — from first principles to RAG, agents, MCP and AI security. Free, no sign-in.
55 guides in Machine learning
Why combining models often beats any single one, and the three main ways to do it.
Machine learning 2 min read 5 Sep 2026 For people
Trend, seasonality, baselines and time-based validation: the fundamentals of predicting future values from past ones.
Machine learning 2 min read 4 Sep 2026 For people
Finding unusual records — fraud, faults, intrusions — with statistics and machine learning, even when examples of anomalies are scarce.
Machine learning 2 min read 3 Sep 2026 For people
How recommendations are made — collaborative filtering, content-based methods and hybrids — and how to evaluate them.
Machine learning 2 min read 2 Sep 2026 For people
Grid search, random search and Bayesian optimisation, plus practical advice on what to tune and how to avoid overfitting the validation set.
Machine learning 2 min read 1 Sep 2026 For people
Chain preprocessing and modelling into one object that prevents leakage and deploys cleanly.
Machine learning 2 min read 31 Aug 2026 For people
The most common reason models look brilliant in testing and fail in production — and how to prevent it.
Machine learning 2 min read 30 Aug 2026 For people
A simple baseline turns a metric into a meaningful result. The baselines to use for common problem types.
Machine learning 1 min read 29 Aug 2026 For people
Reusing a model trained on one task as the starting point for another — the technique that makes deep learning practical with limited data.
Machine learning 2 min read 28 Aug 2026 For people
When and how to adapt a pretrained model to your task, and the alternatives to consider first.
Machine learning 2 min read 27 Aug 2026 For people
How CNNs recognise patterns in images using filters and pooling, and why pretrained CNNs are so widely reused.
Machine learning 2 min read 26 Aug 2026 For people
How RNNs and LSTMs process sequences step by step, why they struggled with long contexts, and what replaced them.
Machine learning 2 min read 25 Aug 2026 For people
The mechanism behind modern language models: self-attention, multi-head attention and positional information, explained intuitively.
Machine learning 2 min read 24 Aug 2026 For people
Seeds, versioned data, tracked parameters and saved environments: how to make results you can trust and repeat.
Machine learning 2 min read 23 Aug 2026 For people
When a model says 80%, does it happen 80% of the time? How to check and fix probability calibration.
Machine learning 2 min read 22 Aug 2026 For people
Building a tree of clusters by merging or splitting groups, reading dendrograms and choosing where to cut.
Machine learning 1 min read 21 Aug 2026 For people
Finding clusters of any shape and flagging noise points using density, with guidance on setting parameters.
Machine learning 1 min read 20 Aug 2026 For people
Soft clustering with probability distributions: how GMMs work, how they're fitted and when to use them.
Machine learning 1 min read 19 Aug 2026 For people
How t-SNE and UMAP project complex data into two dimensions for exploration, and how to avoid misreading the plots.
Machine learning 1 min read 18 Aug 2026 For people
Understanding the two sources of model error, how model complexity affects them, and how to find the right balance.
Machine learning 1 min read 17 Aug 2026 For people