Current students

COMPGI21 - Introduction to Machine Learning

This database contains the 2017-18 versions of syllabuses. Syllabuses from the 2016-17 session are available here.

Note: Whilst every effort is made to keep the syllabus and assessment records correct, the precise details must be checked with the lecturer(s).

CodeCOMPGI21
YearMSc
PrerequisitesIntroductory courses covering linear algebra, calculus, probability theory and programming.
Term1
Taught ByIasonas Kokkinos (100%)
AimsTo have a full understanding of the learning outcomes.
Learning Outcomes

Students will become familiar with the conceptual landscape of machine learning and have developed practical skills to solve real world problems using available software.

Content

Introduction to Supervised Learning

  • Linear Models for regression and classification
  • Concepts of overfitting and regularization, L1 and L2 regularisation
  • Na├»ve Bayes and Logistic Regression
  • Nearest Neighbour classification
  • Boosting, Decision Trees, Random Forests
  • Support Vector Machines

Introduction to Unsupervised Learning

  • K-means
  • Principal Components Analysis
  • Expectation-Maximization, Mixture of Gaussians, Factor Analysis

Deep Learning

  • Neural Networks for regression and classification
  • Unsupervised models: Autoencoders, Generative Adversarial Networks

Method of Instruction

3 hours of Lectures and 2 hour tutorial per week.

Assessment

The course has the following assessment components:

  • Written Examination (2.5 hours, 70%)
  • Coursework Section (30%)

To pass this course, students must:

  • Obtain an overall pass mark of 50% for all sections combined.

Resources

Reading list available via the UCL Library catalogue.