Lecture by professor Lars Kai Hansen, DTU Compute.
Abstract: Machine learning is a set of inference techniques with a focus on prediction. To let the ‘data speak’ machine learning is often based on weak model assumptions leading to the (mis-)conception that it is a black box approach. Indeed, much machine learning research has been devoted to developing expressive representations and algorithms with high statistical and computational efficiency. However, in certain domains - such as systems neuroscience - interpretability and accountability are important for successful applications. I will give an introduction to our tools for understanding machine learning representations and inference and illustrate with examples from neuroimaging.
“Meet DTU Compute” is a series of lectures that offers friendly introductions to hot research topics at DTU Compute given by local experts. The lectures are co-organized together with the DTU Compute Research Academy and PhD School.
Each session starts with lunch (sandwiches) 12:30-13, and for that reason it is necessary to sign up by email to Pia Lauridsen, email@example.com
The lecture is part of a series of seminars organized by the PhD School at DTU Compute, and is a part of the course: 02921 graduate school seminars.