This project aims to describe machine learning fundamentals from an introductory mathematical side, to the models, methods, and algorithms that implement those models. Each subfolder will consist of Jupyter notebooks with an explanation of the math background and of the essential algorithms, and also executable (not restricted to-)Python scripts that apply those algorithms to particular examples.
Also other data science concepts, methods and tools related to machine learning will also be provided.
Machine learning is the generalization of the classic regression problem in statistics. It is the task of estimating a function for
, such that
given observations of
(in the supervised case), where the noise term
is assumed to be such that
. The task is then to find a good estimator of the model parameters:
.