Machine Learning Foundations: A Case Study Approach

This introduction to the specialization provides insights into the power of machine learning and the multitude of intelligent applications you will be able to develop and deploy upon completion. Includes introduction to Python programming and Jupyter notebooks.

Build your first intelligent application that makes predictions from data. Create models that predict house prices from input features. Learn about regression, model evaluation, and implementation using Jupyter notebook.

Create models that predict sentiment class from input features like review text and user profiles. Learn about classification, accuracy evaluation, confusion matrices, and implementation of classifiers.

Examine document representations and algorithms to retrieve similar documents. Learn about document similarity measures, tf-idf, clustering, and build an intelligent document retrieval system.

Learn how to build recommender systems using collaborative filtering and matrix factorization. Explore various techniques for personalized recommendations and build a song recommender system.

Learn about deep learning for image classification and retrieval tasks. Study neural networks, transfer learning with deep features, and build image classifiers and retrieval systems.

Discussion of machine learning deployment, open challenges in the field, future directions, and overview of the rest of the specialization.