The practices applied to each entry, and the checks run over it.
A statement in an entry is backed by a citation, by a figure or derivation in the entry, or by a numerical experiment. Where it rests on an experiment, the script is published beside the term, so the computation can be repeated. A checker reads the entry sentence by sentence and lists statements for which it finds none of these. That list is a working list: it records what has not been backed yet, not a guarantee that nothing remains.
A citation names a location in a work — a section, a numbered result, an example. A citation can name the right work and the wrong location in it, which a check of the bibliography does not detect. The pinpoint is therefore located in the text of the source, and the passage found there is compared with the statement it supports. Two corrections made this way: an identity displayed in Sect. 2.3.1 of Boyd and Vandenberghe had been cited to 2.5.1, where it is proved rather than stated; a definition of completeness had been cited to the Hilbert-space chapter of Bauschke and Combettes, which assumes it, rather than to Sect. 1.12, which states it.
Thirty checkers run over an entry. Some are mechanical: an article that disagrees with the rendered form of an abbreviation, a plural inconsistent with its term, a figure without a caption, text overflowing the margin, notation written out where a macro exists. Others read the prose: a reference with no antecedent, a comparison whose second term is not named, a metaphor that states no checkable claim, a sentence whose removal changes nothing. Most are advisory — they report candidates, and the decision stays with the author.
One word per concept. Where the literature uses one word for two concepts, the entries separate them: a feature transformation maps the feature vector of a data point to another feature vector, while a feature map is the grid of activations produced by one channel of a convolutional layer. Both names are standard in their own literature, which is why the distinction is recorded.
The course edition is licensed CC BY 4.0. It is distinct from the Dictionary of Applied Machine Learning to be published by Springer. Each term page carries a citation block, a typeset PDF, and the Python script for that term.