Statistical Learning

Overview

Learn how to mathematically design, interpret and evaluate statistical models that are designed to learn from data and which underpin subsequent artificial intelligence and machine learning techniques.

Course Details

This course provides an in-depth theoretical introduction to Statistical Learning - the fundamental mathematics and statistics that underpin data science and machine learning models, with wider applications in almost every industry including science, engineering, economics, finance, healthcare, retail, manufacturing, advertising, energy, defence, politics and government. This course explores in detail the major topics in Statistical Learning including linear methods for regression and classification, generalised additive models, tree-based methods, support vector machines, clustering, dimensionality reduction, and other supervised and unsupervised learning techniques designed to model and learn from data. This course is a fundamental pre-requisite in order to design, build, interpret and evaluate applied machine learning models using modern machine learning frameworks including Scikit-Learn and Apache Spark MLlib. It also enables senior data scientists to genuinely understand how machine learning works under-the-hood, beyond simple deployment of existing cloud-based machine learning services, so that suitable features and models are selected based on the specific context of the business problem at hand.

Course Modules

• 1. Statistical Learning Fundamentals
• 2. Probability Theory
• 3. Linear Methods - Regression Part 1
• 4. Linear Methods - Regression Part 2
• 5. Linear Methods - Classification Pt 1
• 6. Linear Methods - Classification Pt 2
• 7. Beyond Linearity Part 1
• 8. Beyond Linearity Part 2
• 9. Tree-Based Methods Part 1
• 10. Tree-Based Methods Part 2
• 11. Support Vector Machines Part 1
• 12. Support Vector Machines Part 2
• 13. Clustering Part 1
• 14. Clustering Part 2
• 15. Dimensionality Reduction Part 1
• 16. Dimensionality Reduction Part 2
• 17. Model Selection

Requirements

• Linear Algebra or equivalent.
• GCSE-level Mathematics or equivalent as a minimum, ideally A-Level Mathematics or equivalent.

Outcomes

• Knowledge of the major mathematical topics in Statistical Learning.
• Knowledge of common supervised and unsupervised learning techniques.
• The ability to select features and models based on the specific context of the business problem.
• The ability to mathematically design, build, interpret and evaluate statistical models designed to learn from structured and unstructured data.
• Foundational mathematical knowledge required to design and build applied machine learning models using relevant software frameworks (e.g. Scikit-Learn, Apache Spark, TensorFlow and Keras) for artificial intelligence use-cases.