Machine Learning and Adaptive Intelligence

This unit aims to provide a deep understanding of the fundamental technologies underlying modern artificial intelligence. In particular it will provide foundational understanding of probability and statistical modelling, supervised learning for classification and regression, and unsupervised learning for data exploration. The teaching consists of two hours of lectures and one of lab classes each week. The lectures are on Tuesdays, the labs on Fridays. The teaching schedule and venue for each week are given below:

  1. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  2. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  3. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  4. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  5. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class (Neil will leave at around 10:25)
  6. Reading Week
  7. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  8. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  9. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  10. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  11. Tuesday 12-14 MAPP-LT11; Friday 10-11 Regent Court G12 Lab Class
  12. Reading Week

Recommended text book

The main course recommended text is Rogers and Girolami’s “A First Course in Machine Learning”. Also useful is Bishop, Pattern Recognition and Machine Learning. Most lectures will provide references to these text, and it will help a lot if you read the relevant sections in your own time.

A further publicly available text is Hastie et. al, The Elements of Statistical Learning.

Pre-requisites

You are expected to have familiarity with basic probability and linear algebra. We will use Python and the ipython notebook on the course, so you are expected to be comfortable with adapting to a new programming environment without specific tuition.

Lecture Slides

The material for the lectures will be posted below before each lecture (including audio and screen capture, where possible). We aim to put up the materials for each week’s lectures at the beginning of week.

Week 1: Uncertainty and Probability

Introduction to Numerical Computing in Python Lab Class

Week 2: Regression

Linear Regression in the Lab

Week 3: Generalization

Generalization Lab

Assignment distributed

Week 4: Classification

Classification Lab

Week 5: Bayesian Inference

Week 6: Reading Week

Week 7: Gaussian Processes

Bayesian Regression Lab