The objective of this class is to introduce undegraduate students to the field of machine learning - a burgeoning area of computer science, and a sub-field of (narrow) artificial intelligence (AI). Machine learning is about the methods and approaches that enable computers to learn, perform tasks, and improve performance on these tasks -- all without being explicitly programmed to do so.
Topics covered
- Introduction - what is Machine Learning (ML)
- The essential role of data
- Discovery - unsupervised and supervised methods, exploratory data analysis, and visualization
- Prediction - inference, classification, and prediction
- Automation - training, testing and validation of ML methods
Lecture style
Every lecture will be broken down into four sections - intuition, theory, practice, and applications. Every topic will be covered theoretically, and hands-on, using Jupyter Notebooks on Google Collaboratory and Python.Recommended Background Material
- Python Programming
- Sckit-learn
- Jupyter Notebooks
- Google Collaboratory