REAPER: A Framework for Materializing and Reusing Deep-Learning Models (E|ASY-Opt INF6)
Third Party Funds Group - Sub project
Acronym: E|ASY-Opt INF6
Start date : 01.01.2017
End date : 31.12.2020
Website: https://www.faps.fau.de/curforsch/efre-easy-opt/
Overall project details
Overall project
EFRE EIASY-Opt - Kompetenz- und Analyseprojekt für die "datengetriebene Prozess- und Produktionsoptimierung mittels Data Mining und Big Data"
Overall project speaker:
Project details
Short description
Short description
Within the framework of the EFRE-E|ASY-Opt subproject, the potential of data mining methods in the area of manufacturing is being investigated. Especially the training of Deep-Learning models is a computationally intensive task, which may take hours or several days. The training time can be shortened considerably by using an already trained model, as long as the goal and source task are closely related. This connection is not yet fully understood.
The aim of this research project is to implement a system called REAPER (Reusable Neural Network Pattern Repository) to support data scientists in storing and reusing already trained deep learning models.
Scientific Abstract
Within the framework of the EFRE-E|ASY-Opt subproject, the potential of data mining methods in the area of manufacturing is being investigated. Especially the training of Deep-Learning models is a computationally intensive task, which may take hours or several days. The training time can be shortened considerably by using an already trained model, as long as the goal and source task are closely related. This connection is not yet fully understood.
The aim of this research project is to implement a system called REAPER (Reusable Neural Network Pattern Repository) to support data scientists in storing and reusing already trained deep learning models.
