Dipl.-Ing. Vincent Latzko

PhD Researcher

Vincent Latzko received his Diploma degree in Electrical Engineering and Information Technology from Technische Universität Darmstadt, with a focus on the fundamental theory of electromagnetic fields and the numerical solution of Maxwell’s equations (www.temf.de) using a multitude of mathematical and algorithmic methods (such as DG-FEM, FDTD, Symplectic or BEM/Integral Equation solvers). He worked extensively in fundamental research at one of Europe’s largest particle accelerator facilities, the GSI Helmholtzcentre for Heavy Ion Research (www.gsi.de).

In his diploma thesis with Prof. PhD Carsten Rother at the computer vision lab dresden he restored distorted depth maps using Regression Tree Fields, a non-parametric Gaussian Conditional Random Field method.
He afterwards focused on analytical approaches for regression problems as well as on data driven, deep learning models.

Contact

Phone: +49 351 463-35337
Email: vincent.latzko@tu-dresden.de
riot: @s1480820:tu-dresden.de

Research Interests

• Machine Learning
• Scaling & Provisioning
• Uncertainty Quantification / Bayesian Thinking
• Compression
• Software Defined Networking / Network Function Virtualisation

Teaching

SS 21

• Communication Networks 2

SS 20

• Communication Networks 2
• ICT for Smart Grids

WS 19/20

• Oberseminar

WS 18/19

• Communication Networks 3
• Problem Based Learning
• Oberseminar
• Mentoring / Grundlagen ET

SS 18

• Traffic Theory
• Electrical and Magnetical Fields

WS 17/18

• Communication Networks 3 / Problem Based Learning
• Mentoring / Grundlagen ET

Supervision

• Analysis of Computation Scaling in a Datacenter (Student Thesis Aaron Winkler)
• Placement and Scalability of Virtual Network Functions (Student Thesis Jiali Sun)
• Predictive Placement of Virtualized Network Functions for Urban Vehicular Routing (Preliminary Title of Master Thesis Giovanni Tancredi Iavarone, of Prof. Antonella Molinaro)
• Learning Coding Schemes (Diploma Thesis Alexander Sarmanow)
• Learning Optimal Congestion Control Algorithms (Diploma Thesis Christian Vielhaus)
• Improving Next-Generation Video Codec Segmentation using Deep Learning Techniques (Master Thesis Cheng Chiang Huang)
• Deep Reinforcement Learning for Traffic Control (Diploma Thesis Johannes Busch)
• Optimising and Learning Coding Parameters (Study Thesis Christian Vielhaus)
• Telepresence Demonstrator – Remote Controlled Car via Augmented Reality (Study Thesis Renbing Zhang, joint supervision with Alexander Kropp)
• Exploring Resilience in-car using Multipath SDN (Study Thesis Florian Kemser)

Review

• IEEE Communications Surveys & Tutorials
• IEEE ComSoc
• IEEE Access
• Wiley

Publications