/Details

EEEM066 - Fundamentals of Machine Learning - Fall 2023/4

Module Overview

Module Purpose: This course offers an introduction to machine learning for individuals keen on the science and technology behind Artificial Intelligence (AI). It aims to lay the groundwork for understanding and building fundamental artificial systems capable of processing various data types and analyzing semantic information. Participants will be introduced to vital learning algorithms in a manner that is easy to grasp.

Provider: Computer Science and Electronic Eng
Module Leader: ZHU Xiatian (CS & EE)

  • Credits: 15
  • ECTS Credits: 7.5
  • Framework: FHEQ Level 7
  • JACs Code: (To be filled)
  • Module Cap: N/A
  • Semester: 1

Workload

  • Independent Learning Hours: 87
  • Lecture Hours: 30
  • Tutorial Hours: 3
  • Laboratory Hours: 10
  • Guided Learning: 10
  • Captured Content: 10

Prerequisites / Co-requisites

None

Module Content

Indicative content includes the following:

  • Introduction to Machine Learning
  • Linear Algebra
  • Regression Methods and Logistic Regression
  • Support Vector Machines
  • Tree-based Machine Learning Models
  • Clustering and Dimensionality Reduction
  • Neural Networks
  • Evaluation Techniques
  • Large Scale Machine Learning
  • Machine Learning System Design

Assessment

Pattern

  • Coursework: 25%
  • Examination: 75% (Online, open book, 4-hour window)

Strategy

The strategy aims to allow students to showcase their understanding and application of machine learning concepts. This encompasses problem classes, assignments, and examinations that test knowledge on machine learning paradigms, system design, and python programming.

Summative Assessment

  • Coursework: 25%
  • Examination: 75%

The exam involves several questions from different course areas, inclusive of sub-questions assessing knowledge, analytical, and design skills. The coursework requires utilizing Python for a well-planned experiment and reporting the outcomes.

Formative Assessment and Feedback

Students receive feedback through:

  • Q&A sessions during lectures
  • Supervised computer laboratory sessions

Module Aims

The module seeks to provide a foundational understanding of modern machine learning principles pivotal in various disciplines including, but not limited to, machine vision, natural language processing, and medical imaging.

Learning Outcomes

Students will develop the following attributes:

  1. Understanding of machine learning principles and the underlying theory
  2. Ability to select and apply appropriate machine learning methods
  3. Skill to mathematically formulate and solve domain-specific problems
  4. Capability to analyze real-world problems and devise algorithmic solutions

Attributes Developed

  • C Cognitive/analytical
  • K Subject knowledge
  • T Transferable skills
  • P Professional/practical skills

Methods of Teaching / Learning

The strategy seeks to equip students with a solid understanding of fundamental learning algorithms, necessary mathematical knowledge, basic programming skills, and problem-solving abilities using Python.

Learning and Teaching Methods

  • Lectures and presentation of new material with in-class discussions
  • Laboratory sessions for hands-on experience
  • Python-based coding assignment with an associated written report
  • Timetabled revision classes

Resources

  • Reading List: Surrey Reading List (EEEM066)
  • Digital Capabilities: Enhancing programming skills through Python and deep learning libraries
  • Employability: Fostering practical deep learning skills addressing specific industrial problems
  • Global and Cultural Capabilities: Covering ethics-related topics around computer vision and addressing data bias and domain adaptation issues

For more details, please refer to the official module description (Add the direct link to your module here).