/chains

Mini python library for machine learning centered around optimizing a cost function using the derivation chain rule

Primary LanguagePythonMIT LicenseMIT

Overview

docs Documentation Status
tests
Travis CI build status Unit test code coverage
package
PyPI Package latest release Updates

Mini machine learning library centered around optimizing a cost function specified as a computation graph. Optimization is done by computing partial derivatives by repetitive application of the chain rule. Hence the name.

Originally created while taking coursera's deeplearning.ai class but I wanted a more "from scratch", "generic" and advanced implementation of the course exercices.

Credits

This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.