Show/hide main menu


Machine Learning for Healthcare Applications

Module code: 7MRI0005
Module credits: 15
Module convenors: Dr Maria Deprez

Educational Aims:

This module will provide students with comprehensive theoretical understanding and computational skills in Machine Learning with focus on application in Healthcare technologies, with the aim of developing:

  • a systematic knowledge and critical awareness of most common machine learning techniques relevant to the current research in healthcare technologies
  • in-depth understanding of the theoretical concepts to enable the students to evaluate and develop critiques of existing solutions, and propose novel approaches.
  • practical computational skills to design original machine learning solutions to problems relevant to healthcare technologies.

Learning Outcomes:

On completion of the course the students should demonstrate:

  • a systematic, comprehensive and critical understanding of machine learning algorithms relevant to current research in Healthcare technologies
  • ability to critically evaluate machine learning solutions and propose novel solutions
  • autonomy and originality in tackling complex machine learning problems relevant to Healthcare technologies
  • practical computational skills to design machine learning experiments to solve complex problems in domains related to Healthcare Technologies
  • ability to advance machine learning knowledge and skills through independent study

Module Description

The module will provide a systematic, comprehensive and in-depth knowledge of modern machine learning approaches to prepare students for solving complex problems relating to Healthcare technologies. Topics will include the Regression (Linear, Nonlinear, Penalised), Classification (Perceptron, Logistic Regression, Support Vector Machines), Dimensionality Reduction and Manifold Learning (Principal component analysis, Independent component analysis, Laplacian Eigenmaps), Ensemble learning (Random Forests, Bagging and Boosting), Clustering (K-means, k-NN, GMM, spectral clustering), Feature selection and extraction, Neural Network and Introduction to Deep learning. 


Summative Assessment

Type Weighting
Written Exam (2 hours) (January)  50%
Coursework (Project)  50%

Formative Assessment








Sitemap Site help Terms and conditions  Privacy policy  Accessibility  Modern slavery statement  Contact us

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454