Prof. Dr.-Ing. Janis Keuper

Forschung

Large Scale Machine Learning

  •  Parallelization of Machine Learning Algorithms
  •  Distributed Machine Leaning
  •  HPC Systems for Machine Leaning

Python for Machine Learning and Analytics

Machine Learning Methods

  •  AutoML
  •  Transfer Learning
  •  Optimization Methods for Deep Learning

Machine Learning Applications

  •  High Level Computer Vision with Deep Learning
  •  Generative Models
  •  Deep Learning in Seismic Imaging 

Projekte

Deep Learning, i.e. deep neural networks (DNN), have become a key technology in recent years. However, the design of new, problem specific network topologies is still a time and compute intensive process. So far, the design of deep learning solutions for specific applications mostly follows a purely heuristic try and error process based on human expert knowledge and experience. Every network topology needs to be built from a large number of layer types and their configuration. Most layers themselves, as well as the employed training methods, have complex parameter spaces (so-called hyperparameters), whose impact on the final DNN performance is as large as the impact of the network topology itself.

In this project, we aim at facilitating a more efficient topology design process, rendering DNNs accessible to unexperienced users. Within this project, besides the management and organizational tasks, me and my group have the task to design and evaluate suitable graph embeddings that facilitate to explore the network topology space in an efficient way.

DeToL is funded by BMBF. Runtime: October 2018 - September 2021.

 

Projekt Webseite: www.detol.de

Carme is an open source framework to manage resources for multiple users running interactive jobs (e.g. Jupyter notebooks) on a Cluster of (GPU) compute nodes.

 

Core Idea: Combine established open source ML and DS tools with HPC back-ends

  • Use containers -> Singularity
  • Use Jupyter Notebooks as main web based GUI-Frontend
  • All web front-end (OS independent, no installation on user side needed)
  • Use HPC job management and scheduler -> SLURM
  • Use HPC data I/O technology -> ITWM’s BeeGFS
  • Use HPC maintenance and monitoring tools

 

Project Website: carmeteam.github.io/Carme/