Machine Learning in Science – Part 1
20 credits
This module will provide an introduction to the main concepts and methods of machine learning. It introduces the basics of supervised, unsupervised and reinforcement learning as applied to regression, classification, density estimation, data generation, clustering and optimal control. It will be taught via two sessions per week through a combination of fundamental concepts and hands-on applications.
Machine Learning in Science – Part 2
20 credits
This module will cover more advanced topics following from Machine Learning in Science Part 1, specifically the concepts and methods of modern deep learning. Topics include deep neural networks, CNNs, RNNs, GANs, LLMs, autoencoders, transfer learning, reinforcement learning, interpretable machine learning and Markov decision processes, cleaning data and handling large data sets The main project for the module is the self-driving PiCar, as seen in this video.
Chemistry Research Project
This module will give students the opportunity to undertake a research project in Chemistry. A wide range of projects will be available and students will be offered a selection of research areas. All projects will require a review of relevant published work and the planning and execution of a research topic under the guidance of two supervisors. Students will present their findings orally and in a written report.
Advanced Quantum Calculations
In this module, you will explore the theory behind quantum-chemical calculations, including Hartree-Fock and density-functional theories, electron correlation and relativistic effects.
Through hands-on computational lab sessions, you’ll learn to design, run and interpret simulations, applying quantum calculations to investigate molecular structure, properties and reactivity. You’ll gain experience using quantum chemistry software, the Linux operating system and shared high-performance computing resources.
AI for Drug Design
In this module, you will learn about the field of drug design, particularly the aspects where computational approaches, and especially AI-based techniques, can be applied. You will explore quantitative structure-activity relationships, molecular docking, biomolecular simulation and protein structure prediction.
You will consider wider implications, such as AI and ethics in molecular discovery applications. You’ll learn about a range of applications of machine learning to drug design through some computer laboratory sessions.
Molecular and Materials Modelling
In this module, you will learn how computational modelling techniques are applied to molecules and functional materials, such as semiconductors and energy materials. You’ll explore their structure-property relations and how atomistic simulations can provide insights that are critical to material design, development and optimisation.
Through hands-on lab sessions, you’ll gain experience with methods including quantum chemical calculations, molecular dynamics and machine-learned models.
Big Data and Learning Technologies
In this module, you will explore the principles and technologies that underpin the field of Big Data, where the volume, variety and complexity of data demand solutions beyond the capabilities of a single computer. You will learn how to capture, store, process, search, analyse and visualise large-scale data using modern tools and frameworks.
You will compare SQL and NoSQL databases, gaining insight into when and why to use each type. You will also be introduced to Big Data frameworks, including the MapReduce programming model and technologies from the Hadoop ecosystem and Apache Spark. You will work with Spark’s APIs (RDDs, DataFrames and Datasets) using Python and/or Scala to build distributed applications.
Finally, you will apply data mining and machine learning techniques at scale, using Apache Spark’s MLlib to implement algorithms such as Decision Trees, Random Forests and k-means clustering. You will also learn how to preprocess data and work with data streams to generate meaningful insights from complex datasets.
Statistical Foundations
In this module, the fundamental principles and techniques underlying modern statistical and data analysis will be introduced. You will gain experience in using a statistical package and interpreting its output. The course will cover a 'common core' consisting of:
- statistical concepts and methods
- linear models
- probability techniques
- Markov chains
Enterprise for Scientists
Explore the journey from technical innovation to successful commercial enterprise. In this module you will gain insight into the key factors that drive innovation, including idea evaluation, intellectual property, market awareness, and strategic management. Emphasis is placed on understanding the pathways to market from both academic and industrial perspectives.
You will be given the opportunity to demonstrate your skills in creative thinking, persuasive communication, and selling skills by developing and pitching a new product, service, or business concept to a target audience. You’ll critically assess how large chemistry-based companies manage innovation, and explain how organisational structures and strategies are used to generate value for both the company and its customers.
The module provides you with the necessary skills and knowledge for real-world application after graduation.
Molecular Interactions and Supramolecular Assembly
In this module you’ll learn about the importance of intermolecular forces, across a wide cross-section of subject areas from biology through to supramolecular chemical systems.
You'll study molecular organisation, assembly and recognition in biological and supramolecular systems.
In addition to appreciating the rich chemistry underlying self-assembling systems, you'll learn about the phenomena that impact on the properties of materials and important interactions in biology.
You'll attend two lectures per week in this module.