KIT Career ServiceAbschlussarbeiten am KIT

High Performance EM for Gaussian Mixture

Forschungsthema/Bereich
Artificial Intelligence
Typ der Abschlussarbeit
Bachelor / Master
Startzeitpunkt
-
Bewerbungsschluss
30.06.2028
Dauer der Arbeit
4 months(BSc) - 6 months(MSc)

Beschreibung

High performance Expectation Maximization (EM) for Gaussian Mixture is compelling because it unlocks scalable, accurate density estimation for modern datasets. Faster E and M steps enable real time clustering, anomaly detection, and soft classification
in streaming and interactive applications. Optimized linear algebra, vectorization, and GPU acceleration reduce runtime and energy, broadening feasibility on edge and cloud. Careful numerical stability, batching, and memory layout improve convergence
and robustness on large datasets. Parallelized responsibilities, batched covariance updates, and efficient mixture normalization increase throughput without sacrificing precision. Such implementations empower rapid model selection, online updates, and hyperparameter sweeps, driving better decisions in diverse range of applicatioons.

Voraussetzung

Voraussetzungen an Studierende
  • There are no hard constraints but the more programming and math you know the more you can have fun while doing the project.

Studiengangsbereiche
  • Ingenieurwissenschaften
    Informatik


Betreuung

Titel, Vorname, Name
Ali Darijani
Organisationseinheit
Computer Science(IAR/IES)
E-Mail Adresse
ali.darijani@iosb.fraunhofer.de
Link zur eigenen Homepage/Personenseite
Website

Bewerbung per E-Mail

Bewerbungsunterlagen

E-Mail Adresse für die Bewerbung
Senden Sie die oben genannten Bewerbungsunterlagen bitte per Mail an ali.darijani@iosb.fraunhofer.de


Zurück