Skip to content
Deep Topology Learning
Branch: master
Clone or download
Latest commit e39329d Apr 15, 2019
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
2000px-Albert-Ludwigs-Universität_Freiburg_2009_logo.svg.png resze logos Oct 21, 2018
2000px-Uni-mannheim.svg.png resze logos Oct 21, 2018
BMBF.jpeg Add files via upload Oct 9, 2018
Fraunhofer_ITWM.jpg resze logos Oct 21, 2018
LICENSE
README.md
_config.yml
lrz_wortbild_d_blau-230.png
psiori-logo-white-pix.png

README.md

Deep Topology Learning (DeToL)

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.

Partners

https://www.itwm.fraunhofer.de/de/abteilungen/hpc/Daten-Analyse-Maschinelles-Lernen.html

Publications

Contact

info@detol.de

You can’t perform that action at this time.