XClose

UCL Computer Science

Home
Menu

Module descriptions for Artificial Intelligence for Sustainable Development MSc

Find provisional module information for the new Artificial Intelligence for Sustainable Development MSc below.

New modules

Artificial Intelligence for Sustainable Development MSc is a brand-new programme launching at UCL this September. You can learn more about the new modules from the summary descriptions below, which are provisional and subject to change. Final detailed versions will be added to UCL’s Module Catalogue by the end of March 2022.

Apply for the Artificial Intelligence for Sustainable Development MSc

Foundations of Artificial Intelligence

15 credits, Term 1, available to taught postgraduate students

This module covers the fundamentals of machine learning, from theoretical and algorithmic perspectives. The module starts with an introduction to statistical learning theory, including the notions of risk, generalisation bounds, model complexity (VC dimension, Rademacher complexity, ...), bias-variance trade-off, overfitting, regularisation, and many others. Classical results will be proved and discussed. The second half of the module will present classical machine learning algorithms, such as linear regression, penalised regression (Lasso, Ridge), decision trees and random forests, boosting, k-nearest neighbours, support vector machines, Bayesian methods, deep neural networks and principal component analysis, to name but a few.

Assessments:

  • 70% Examination
  • 30% Coursework

Probabilistic Modelling

15 credits, Term 1, available to taught postgraduate students

This module provides a broad introduction to probabilistic modelling. The module starts with a review of probability theory and Bayesian reasoning, before moving to more advanced techniques for approximate Bayesian inference (variational inference, expectation propagation, sampling, to name a few) and finally covering Bayesian machine learning models such as Gaussian processes and Bayesian neural networks.

Assessments:

  • 60% Examination
  • 40% Coursework

Deep Representations and Learning

15 credits, Terms 1, available to taught postgraduate students

This module covers the fundamentals of state-of-the-art neural networks architectures and the foundations of deep learning algorithms, introducing in detail feedforward neural networks, as well as more advanced topics such as convolutional neural networks, autoencoders, recurrent neural networks, generative adversarial networks and graph neural networks. Students will also be introduced to concepts related to training and modelling with such architectures: backpropagation, regularisation, hyper-parameter tuning as well as optimisation techniques. These core principles and algorithms will be presented alongside coding challenges and example applications.

Assessments:

  • 60% Examination
  • 40% Coursework

Applied Artificial Intelligence

15 credits, Term 2, available to taught postgraduate students

This module aims to give a broad introduction to the rapidly developing field of AI covering a range of approaches (modern, classical, symbolic, and statistical). Students will learn the theory and practice of classical AI techniques covering problem representation, search-based AI, knowledge representation and logic-based information technologies, as well as more novel reasoning and planning strategies, including hybrids of classical AI with modern machine learning such as symbolic neural networks.

Assessments:

  • 40% Coursework
  • 60% Examination

Artificial Intelligence for Domain-Specific Applications Project Preparation

15 credits, Term 2, available to taught postgraduate students

This module aims to prepare the students for the regular 3-months MSc project. The students will have already chosen a project before the beginning of this course. This module includes taught research methods sessions during which students will learn the practical skills essential for undertaking their independent MSc research project.  In addition, the students will be introduced to basic descriptive and inferential statistics with the purpose of enabling them to understand and evaluate the basic research methodology and simple statistical procedures used in research papers. Students will be encouraged to apply and interpret the statistical procedures learned in this course to the data associated with their project. This module will allow the students to complete project definition, literature searches and aggregation, dataset identification for their assigned MSc Project and consequently understand the rationale behind the numerous experimental studies in the literature. Ethical considerations and implications of using Machine Learning and AI for application in HB/SD will also be covered during this module. At the end of the module, students will be expected to apply their understanding of methodology to critique existing research, design their own research, carry out their own analysis and communicate clearly with academic specialists and non-specialists.

Assessments:

  • 50% Coursework 1
  • 50% Coursework 2

Artificial Intelligence for Remotely Sensed Applications

15 credits, Term 2, available to taught postgraduate students

Machine learning has been widely used lately in remotely sensed data analysis, for urban management, geosciences and biomedicine, among others. This module provides an in-depth look at applying machine learning to multimodal sensor data analysis and a practical and comprehensive coverage of applications and technologies in this field, from data preparation to results mapping. The course will allow students to develop the skill set to design and implement such learning systems for remote sensing applications in practice.

Assessments:

  • 60% Coursework 1
  • 40% Coursework 2

Artificial Intelligence for Computational Pathology

15 credits, Term 2, available to taught postgraduate students

Analysis of tissue and blood samples under a microscope is essential to many areas of pathology from research, clinical diagnosis, prognosis and treatment selection. Integration of digital slides into the clinical workflow and recent advances in Machine Learning and AI have the potential to overcome the country wide shortage of pathologists and drastically transform pathology clinical pathways. This module  provides an in-depth look at developing and validating AI and Machine Learning approaches to automatically analyse digital pathology slides of biological specimens with the goal of improving early diagnosis and determining prognosis.

Assessments:

  • 60% Coursework 1
  • 40% Coursework 2

Accountable, Transparent, and Responsible Artificial Intelligence

15 credits, Term 2, available to taught postgraduate students

This module covers the implications of Artificial Intelligence and introduces novel research strategies for building accountable, transparent and responsible intelligent machines. Among others, this course introduces concepts related to risk and decision making with AI, fair and unbiased machine learning algorithms, safety and trust in human-machine systems, policy-making with and for AI and transparency and interpretability of AI technology, all current open challenges for the artificial intelligence community and with a crucial role to play in building a sustainable society.

Assessments:

  • 50% Coursework 1
  • 50% Coursework 2

MSc Artificial Intelligence for Sustainable Development Project

60 credits, Terms 2 & 3, available to taught postgraduate students

This three-month individual-project structure is aimed to consolidate our students PGT knowledge in AI and ML, acquired during First and Second Terms of the MSc Programme, by immersing them within the sustainable development domain environment. 
Students will carry out a substantive piece of work that will result in a comprehensive written report along with demonstrable protypes, processes, or products. The module provides the platform to demonstrate the ability to formulate hypothesis and investigate a research question of relevance to the application of AI technologies to the sustainable development domain, and to analyse and present the findings of that research.

Assessments:

  • 100% Report