The University of Sheffield
Department of Computer Science

COM4509 Machine Learning and Adaptive Intelligence

Summary

The module is about core technologies underpinning modern artificial intelligence. The module will introduce statistical machine learning and probabilistic modelling and their application to describing real-world phenomena. The module will give students a grounding in modern state of the art algorithms that allow modern computer systems to learn from data.

Students should be aware that there are limited places available on this module.

Session Autumn 2021/22
Credits 15
Assessment
  • Formal examination [LO1, LO2]
  • Assignment [LO3, LO4]
Lecturer(s) Dr Mauricio Alvarez & Dr Haiping Lu
Resources
Aims This unit aims to provide a deep understanding of the fundamental technologies underlying modern artificial intelligence. In particular, it will provide a foundational understanding of
  • data science,
  • machine learning.
Objectives

By the end of the unit, a candidate will be able to demonstrate the ability to

  1. understand of probability theory and how it relates to uncertainty in modern artificial intelligence,
  2. understand when and how to implement the appropriate learning paradigm for a given application,
  3. implement a range of fundamental and/or advanced machine learning algorithms on simple problems,
  4. deploy appropriate machine learning algorithms to solve real-world problems.
Content
  • Introduction to machine learning
  • End-to-End machine learning
  • Linear regression
  • Decision trees and ensemble methods
  • Automatic differentiation
  • Logistic regression
  • Neural networks
  • Unsupervised learning
  • Deep generative models
  • Other topics
Restrictions The maximum number of students allowed on the module is 40.
Teaching Method There will be formal lectures and lab classes. These classes may involve computer-based problem solving, examples and MCQ. The lectures and example classes will run concurrently, covering similar topics, with the theory being laid out in the lectures, and application of the theory taking place in example classes.
Feedback Students will receive feedback on their assignments and quizzes through Blackboard and in the Lab Sessions.
Recommended Reading
  • S. Rogers and M. Girolami, A First Course in Machine Learning
  • C. Bishop, Pattern Recognition and Machine Learning
  • D. Barber, Bayesian Reasoning and Machine Learning
  • R. Duda, P. Hart and G. Stork, Pattern Classification
  • A. Geron, Hands-On Machine Learning with Scikit-Learn & TensorFlow
  • I. Goodfellow, Y. Bengio, A. Courville. Deep learning. MIT press
  • Flach, Peter. Machine learning: the art and science of algorithms that make sense of data. Cambridge University Press, 2012.
  • Zaki, Mohammed J., and Wagner Meira Jr. Data Mining and Machine Learning: Fundamental Concepts and Algorithms. Cambridge University Press, 2020.