Machine-Learning-Specialization-Coursera

This repository holds completed assignments, practice quiz answers, and optional lab notebooks for the Machine Learning Specialization offered by Stanford University and Deeplearning.ai on Coursera. The specialization was created by Andrew Ng, a well-known machine learning researcher and educator. The content here was completed in 2022 and covers the full three-course sequence.

The first course focuses on supervised learning, which is the kind of machine learning where a model learns from labeled examples. It walks through predicting continuous values (called regression) and sorting items into categories (called classification), using techniques like linear regression and logistic regression. Labs in this course are written as Jupyter Notebooks, which are interactive documents mixing code, explanations, and charts.

The second course covers more advanced training practices, including how to tell whether a model is learning too narrowly from its training data, how to choose settings that control the learning process, and how to build decision trees, which are models that make predictions by asking a series of yes-or-no questions about the input data.

The third course introduces neural networks and deep learning, covering how to build multi-layer models, apply them to practical tasks, and understand what is happening inside them. The repository is organized by course and week, with each folder containing the relevant notebook files.

This is a solutions repository, meaning it shows completed answers rather than blank starting templates. It is most useful to someone who is already working through the same specialization and wants to compare their approach or get unstuck on a specific exercise. The author also links to a separate companion repository covering the mathematics background for these topics, for those who want a deeper grounding before or alongside the course material.