The field of machine learning is concerned with the study of methods for developing computer programs that are able to learn from examples or from prior experience. Machine learning lies at the basis of many of the recent successes in artificial intelligence, with applications ranging from self-driving cars to digital assistants and search engines. This module will serve as a general introduction to machine learning, covering both traditional methods such as decision trees and support vector machines and more recent neural network based techniques. The main focus will be on application oriented aspects of machine leaning, such as how to implement key machine learning techniques, how to choose which technique to use in a given situation, how to pre-process data, and how to evaluate the performance of a machine learning system. In addition to these technical topics, the module will also cover some important ethical considerations, including how the choice of training data can introduce unwanted biases in real-world applications.

1. Implement and evaluate machine learning methods to solve a given task
   
    
2. Explain the basic principles underlying common machine learning methods
   
    
3. Choose an appropriate machine learning method and data pre-processing strategy to address the needs of a given application setting
   
    
4. Reflect on the importance of data representation for the success of machine learning methods
   
    
5. Critically appraise the ethical implications and societal risks associated with the deployment of machine learning methods
   
    
6. Explain the nature, strengths and limitations of an implemented machine learning technique

The module will be delivered through a combination of lectures, supervised lab sessions and tutorials as appropriate. You will be expected to attend all timetabled sessions and engage with online material.

You will be guided through learning activities appropriate to your module, which may include:

on-line resources that you work through at your own pace (e.g. videos, web resources, e-books, quizzes),

sessions to work with other students and staff (e.g. lectures, live streaming of presentations, live-coding, team meetings)

face to face group sessions (e.g. help classes, feedback sessions)

Subject-Specific Skills: • During this module you will gain experience in implementing machine learning tools, taking advantage of existing libraries where appropriate • Through practical examples you will learn how to assess the potential and limitations of machine learning technology

Professional & Practical Skills: • You will enhance your communication skills by disseminating a machine learning project in an effective form (e.g., report or presentation) • You will practice your communication and team working skills and be able to communicate complex ideas effectively to a range of audiences

Transferable/Employability Skills: • You will develop investigative skills and the ability to design appropriate solutions to problems • You will develop your critical thinking skills by considering which tools are appropriate in what contexts, and what are the possible ethical, social or economical implications

Summative Assessments: • 60% - Machine Learning group project You will be carry out a group project on a specific topic. You will be provided with a dataset and a supervisor for your project, and the project will design a machine learning pipeline to solve the given task. (L.O. 1-6). • 40% - Class Test Fundamental knowledge gained during the module will be assessed by a class test

Formative Assessments: 1) Programming Exercises and Workshops: Weekly programming exercises and practice sessions will allow you to practice your use of machine learning tools, helping you build confidence and competence in creating machine learning pipelines.

These formative assessments are designed to provide continuous feedback and support, helping you to develop the necessary skills and knowledge to excel in the summative assessments.

Students will be provided with reassessment opportunities in line with University regulations.

Pre-processing datasets: feature selection, dimensionality reduction, eliminating bias, dealing with class imbalance and missing data

Evaluating machine learning methods: designing experiments, cross-validation, statistical testing, evaluation metrics (e.g. accuracy, precision, recall, F1, AUC, NDCG, MAP)

Bias-variance tradeoff, no free lunch theorem

Meta-learning (e.g. boosting, bagging, stacking)

Decision trees, random forests

Support vector machines, kernels

Introduction to neural networks, activation functions, regularization, dropout

Standard neural network architectures (e.g. autoencoders, convolutional networks, recurrent networks)