All topics

Four subject groups cover every note on this site. Each group lists the notes filed under it.

TensorFlow and neural networks

How a TensorFlow program is structured, what the training loop actually repeats, and how to tell a model that is learning from one that is memorising.

1. TensorFlow graphs and sessions
2. What a training loop repeats

Machine learning workflow

The plain mechanics either side of the model: preparing columns so they compare fairly, reading the result honestly, and picking the lighter tool when it fits.

1. Feature scaling before fitting
2. Reading a confusion matrix
3. Overfitting and regularisation
4. Choosing a Python ML workflow

D3 and data visualisation

Scales, axes, force simulations and text layouts, described as the small functions they are rather than as chart recipes.

1. Force directed graphs in D3
2. D3 scales and axes
3. Building a word cloud from text

JavaScript data stack

What the Node and MongoDB layer around a model is responsible for, and what it should refuse to take on.

1. Node and MongoDB under a model
2. Indexing MongoDB for read-heavy work
3. Keeping a Node service non-blocking