// the find
AntonioErdeljac/python-tensorflow-google
Notes taken from Google Machine Learning Course provided to public for practice & correction.
A set of study notes from Google's Machine Learning Crash Course, written as a wiki of section-by-section summaries from linear regression through embeddings, with a handful of Python TensorFlow and pandas scripts alongside. It suits someone working through the same course who wants a second explanation of each topic and a few runnable examples.
- The wiki follows the course order closely, so each section's summary maps directly to a point in the official material and can be read as a revision guide.
- The Python files map to specific sections (feature_crosses.py, synthetic_features_and_outliers.py, validation.py), so the code is tied to concepts rather than being generic boilerplate.
- The README's section summaries name the actual concepts covered, such as L1 versus L2 sparsity and ROC/AUC, so you can see quickly whether a given topic is covered.
- The notes live in the GitHub wiki, not the repo, so they aren't versioned with the code, can't be reviewed in a PR, and drift from the scripts without anyone noticing.
- The last push was in February 2023 and the code targets an older TensorFlow API surface. Expect deprecation warnings or outright breakage on current TensorFlow and pandas.
- The scripts have no requirements file, no tests, and no way to run them besides reading them. For practice, that means you are on your own to get them running and to check the results.
- The README's section blurbs are one-line teasers. The substance is in the wiki pages, so the repo on its own tells you little about the depth of the notes.