CSU44061 – Machine Learning

Module CodeCSU44061
Module Name Machine Learning
ECTS Weighting [1]5 ECTS
Semester TaughtSemester 1
Module Coordinator/s  Professor Douglas Leith

Module Learning Outcomes

On successful completion of this module, students will be able to:

  1. Understand what machine learning is and how it works;
  2. Understand and be able to apply machine learning algorithms such as linear regression, logistic regression, SVM, kNN and (deep) neural networks;
  3. Be able to effecively evaluate the performance of machine learning methods;
  4. Apply machine-learning frameworks (e.g. scikit-learn) to solve real-world problems.

Module Content

  • Prediction using machine learning;
  • Choice of features, including for text, images, time series;
  • Model selection (e.g. linear, kernel, neural net);
  • Learning as empirical risk minimisation;
  • Common machine learning techniques (linear regression, logistic regression, SVMs, kernel trick, neural nets, convolutional neural nets, kNN, k-Means);
  • Evaluating machine learning methods (cross-validation, bootstrapping, ROC, use of a baseline);
  • Practical experience of applying machine learning methods to real data.

Teaching and Learning Methods

Lectures and coursework.

Assessment Details

Assessment ComponentBrief DescriptionLearning Outcomes Addressed% of TotalWeek SetWeek Due
ExaminationAssignment Applying ML MethodsLO1, LO2, LO3,
LO4, L05
50%N/AN/A
CourseworkWeekly Assignments, Individual ProjectLO1, LO2, LO3,
LO4, L05
50%N/AN/A

Reassessment Details

Assignment (100%).

Contact Hours and Indicative Student Workload

Contact Hours (scheduled hours per student over full module), broken down by: 22 hours
Lecture22 hours
Laboratory0 hours
Tutorial or seminar0 hours
Other0 hours
Independent Study (outside scheduled contact hours), broken down by:94 hours
Preparation for classes and review of material (including preparation for examination, if applicable)44 hours
Completion of assessments (including examination, if applicable)50 hours
Total Hours116 hours

Recommended Reading List

N/A

Module Pre-requisites

Prerequisite modules: STU33009

Other/alternative non-module prerequisites: Python programming. Basic knowledge of probability and statistics at a level similar to that provided by module STU33009.

Module Co-requisites

N/A

Module Website

Blackboard

Links to classes for the first two weeks (for students who may wish to switch to this module):

Blackboard collaborate link.

The lecture slides are also available at www.scss.tcd.ie/doug.leith/CSU44061.