If you find any data displayed on this website that should be amended, please contact the Curriculum Management Team.
Module Title
LM Data Analytics and Statistical Machine Learning
School
School of Medical Sciences
Department
Inst of Cancer / Genomic Sci
Module Code
02 29783
Module Lead
Dr. Mamunur Rashid
Level
Masters Level
Credits
20
Semester
Semester 1
Pre-requisites
Co-requisites
Restrictions
None
Exclusions
Description
Data analytics and statistical machine learning is a broad introductory module. It will introduce concepts from statistical machine learning (ML), with the aim to provide an in-depth understanding of classical supervised and unsupervised learning models. It will cover analysis of algorithms, implementation, optimization and explain how to structure ML projects. This will allow students to start applying ML techniques to solve problems. Students will develop understanding how to select appropriate ML tools for a given tasks/data types. Data Analytics will build on statistical machine learning concepts, with the main aim to provide hands on experience with health and biomedical data. This will give understanding what are the basic blocks of data analysis using machine learning. This will cover various data management approaches such as quality control, tools to deal with missing data, data normalization and to visualize data. It will also introduce common techniques to evaluate model performance and to carry out model selection using frequentist and Bayesian approaches. Students will further develop their programming skills using python and R languages.
Learning Outcomes
By the end of the module students should be able to:
Demonstrate a good understanding of complexity of omics and clinical data and their management including their semantic representation
Demonstrate an in-depth understanding and ability to perform Data integration, mining and analysis
Demonstrate conceptual understanding of Computing, Algorithms and Programming that enables the student to evaluate methodologies and develop critiques of them and, where appropriate, propose new methods
Understand the complexity of information available to enable the integration of diverse data types
Demonstrate self-direction and originality in tackling and solving problems to perform the appropriate Modelling and Optimization
