Course description
This course is specifically tailored for biologists who want to apply machine learning and mathematical modelling on life science data. You will learn the fundamentals of machine learning and also acquire practical experience on a wide variety of techniques for regression and classification modelling using the R environment.
Machine learning is a rapidly expanding form of artificial intelligence (AI) which has found many applications in the field of Biosciences. Delivered by world-leading expert data scientists, course participants will have the opportunity to learn the fundamentals of machine learning using a practical hands-on approach. We will be covering generalised linear regression, penalised regression, decision trees and random forests, support vector machines, and artificial neural networks.
Through a series of practical sessions, you will have the opportunity to use a range of biological datasets from different omics platforms to develop and validate prediction models for classification and numeric prediction purposes. All practical sessions will be delivered using the R environment.
Upcoming start dates
Suitability - Who should attend?
This training is suitable for postgraduate students and professionals in AgriFood, medical and molecular life-sciences who want to learn best practices for predictive modelling on datasets from omics platforms using machine learning in the R environment.
Outcome / Qualification etc.
On completion of this course a participant will be able to:
- Apply state-of-the-art best practices in machine learning to fit the purpose of the analysis.
- Develop classification and regression models based on multivariate biological datasets using R and critically assess model performance and robustness.
- Apply data transformation and optimisation techniques to improve model performance and minimise loss.
- Derive biological relevant information from biological datasets.
Training Course Content
Core content
- Supervised Multivariate data analysis: model training, optimisation and evaluation,
- Multivariate Classification: Binary and multi-class predictive modelling such as SIMCA and PLS-DA,
- Introduction to Machine Learning: Explain the concept of machine learning and differences with statistically based algorithms,
- Classification and Regression modelling: Machine learning algorithms used for classification and regression purposes and gain practical experience building prediction models using a variety of omics datasets.
Course delivery details
The total length of the course is 2.5 days and consists of several theoretical and practical workshops with comprehensive tutorials being delivered throughout the course covering introduction to Machine Learning and Predictive Modelling. The course will take place in a computer lab, and delegates will be supported by the tutors and teaching assistants at all times.
Request info
Cranfield University
Cranfield is a specialist postgraduate university that is a global leader for education and transformational research in technology and management. We have many world-class, large-scale facilities, including our own global research airport, which offers a unique environment for transformational education...