Lecture: Numerical Algorithms in Computer Vision and Machine Learning (IN2384)
SS 2020, TU München
Lectures will start in November and will be held synchronously in Zoom. The lecture is offered in English. More details and announcements can be found in Moodle.
Registration
If you plan to attend, please register for the course in TUMonline.
Later during the semester you will have to register for the exam.
Course Content
This module focuses on numerical methods that frequently occur in the fields computer vision (CV) and machine learning (ML). In addition to algorithms, this module will also cover modelling aspects that are relevant for solving practical problems in CV and ML. The contents include: - Error analysis and conditioning of problems - Linear systems (solvability, algorithms, stability, regularisation), and applications and modelling in CV and ML (e.g. linear regression, image alignment, deconvolution) - Spectral methods (eigenvalue decomposition, singular value decomposition, respective algorithms), and their applications and modelling in CV and ML (e.g. clustering, Procrustes analysis, point-cloud alignment, principal components analysis) - Numerical optimization (gradient-based methods, second-order methods, large-scale optimization) and applications and modelling in CV and ML.