Annotation
The past decade has seen a big increase in the use of machine learning (ML), a major subfield of artificial intelligence, to tackle the challenging problems like self-driving cars, logistic planning, aerospace design, satellite imagery segmentation, cancerous tissue detection, drug design,protein folding etc. Life sciences are still riddled with many difficult problems and the application of these new methods across all branches promises big leaps in our understanding of nature.
The course Machine Learning in Biology will provide an overview of current state-of-the-art machine learning methods and their application to biological problems. Using several popular methods, we will focus on explaining the key concepts and how the methods can be used to gain insight into complex datasets. Understanding of the key concepts is necessary for successful application of machine learning methods to one’s own data, starting with collection, the choice of appropriate methods and finally interpreting the results. We will present recent research papers that applied machine learning in biology to provide examples how different ML methods can be used. At the end of the course, participants will try to propose an ML solution to a specific biological problem.
After finishing the course, students should be able to see their scientific problem through the optics of the machine learning paradigm. That will make it easier to understand whether ML is suitable for their problem, direct them to develop their own ML solution or at least help them communicate their ideas to a data scientist, and subsequently to interpret the results. The course is suitable for students from all fields of biology, no programming experience is required.