Machine Learning and AI for the Sciences - Towards Understanding

Explore machine learning and AI applications in sciences through this 59-minute lecture by Klaus-Robert Müller from Technische Universität Berlin. Delve into the enabling role of ML and AI in neuroscience, medicine, and physics, focusing on challenges and opportunities presented by large and complex data sets. Discover how interpretable ML models can enhance understanding in quantum chemistry. Examine concepts like relevance propagation, generalization error, and brain-computer interfaces. Investigate the Schrödinger equation, kernel retrogression, and deep neural networks in scientific contexts. Learn about prediction quality, molecular dynamics, and the scaling of nonlinear models. Gain insights into the perspectives and limitations of ML and AI in scientific research and industry applications.

Intro
Example
Relevance Propagation
Relevance Conservation
Generalization Error
Age Estimation
Texts
How can you judge
My ultimate hobby
Brain computer interface
Change gears
IPAM Institute
Schrodinger Equation
Representation
Kernel Retrogression
Prediction Quality
Deep Neural Network
Coolant Distance
Scaling Model
Molecular Dynamics
NonLinear Models