Go back to the main page

Table of contents

• Machine Learning and Neural Networks (CM3015)
  • Professor(s)
  • Topics covered
  • Assessment
  • Module specification
  • Recognition of Prior Learning
  • Past exams
  • Syllabus
  • Resources
    • Notes
    • Textbooks used in this Module

---

Machine Learning and Neural Networks (CM3015)

This module provides a broad view of machine learning and neural networks. You will learn how to solve common machine learning problems such as regression, classification, clustering, matrix completion and pattern recognition. You will learn about neural networks and how they can be trained and optimised, including an exploration of deep neural networks. You will learn about machine learning and neural network software libraries that allow you to develop machine learning systems rapidly, and you will learn how to verify and evaluate the results.

Professor(s)

• Dr. Jamie Ward
• Dr. Tim Blackwell

Topics covered

• Regression and classification
• Features and distances
• Supervised clustering
• Evaluation: accuracy, precision, recall and cross validation
• Dimensional reduction: principal component analysis
• Matrix completion
• Unsupervised clustering
• Multi-Layer Perceptrons and back progagation
• Network optimisers
• Deep and recurrent networks

Assessment

Coursework only (Type II).

Module specification

• Module specification

Recognition of Prior Learning

• At the time of this writing, you can apply for automatic RPL for this module if you obtain the IBM AI Engineering Professional Certificate.

Past exams

• See past-exams/cm3015-mlnn at binary-assets.

Syllabus

• Syllabus

Primary programming language

Python

Resources

Notes

• Visit this page of world-class/notes.

Textbooks used in this Module

• Deep Learning with Python (1st ed); Chollet, François (2017); Manning, New York.