Machine Learning in Biotechnology

Overview

What you will study

The Machine Learning in Biotechnology offered by KTH Royal Institute of Technology covers the foundations of data-based modeling and builds on this topic with machine learning modules relevant to genomics, protein sciences, and imaging. The course contains lectures and hands-on programming exercises, introducing distinct machine learning modalities. We cover supervised learning and unsupervised learning, and consider challenges and possibilities in applying these methods to biological data. At the end of the course, the participants are expected to have a broad knowledge of different machine learning techniques, concrete understanding of how to implement data based models, and how these tools can be used in the context of biotechnology.

After completion of the course, the students shall have knowledge to:

• Explain the concepts of artificial intelligence/machine learning, including supervised and unsupervised learning, deep neural networks, and optimization.

• Apply machine learning algorithms to a range of data types and domains, including images and genomic data, to solve real-world problems related to biotechnology.

• Evaluate the performance of machine learning models using appropriate metrics and techniques, and interpret the results to draw meaningful conclusions.

• Identify ethical and societal implications of machine learning, including issues related to fairness, privacy, and accountability.

• Communicate machine learning concepts and results effectively to both technical and non-technical audiences, using appropriate visualizations and language.

• Explain how machine learning could begin to be integrated into their own research.