Using Deep Learning to Replace Domain Knowledge

TUM published a new article about using AI to optimize network communication at the 25th IEEE Symposium on Computers and Communications (ISCC)!

Complex problems like the prediction of future behavior of a system are usually solved by using domain knowledge. This knowledge comes with a certain expense which can be monetary costs or efforts to generate it. We want to decrease this cost while using state of the art machine learning and prediction methods.

Our aim is to replace the domain knowledge and create a black-box solution that offers automatic reasoning and accurate predictions. Our guiding example is packet scheduling optimization in Vehicle to Vehicle (V2V) communication. Within the evaluation, we compare the prediction quality of a labour-intense whitebox approach with the presented fully-automated blackbox approach.

To ease the measurement process we propose a framework design which allows easy exchange of predictors. The results show the successful design of our framework as well as superior accuracy of the black box approach.

You can find the article here:

Lübben, Christian and Pahl, Marc-Oliver and Khan, Mohammad Irfan, “Using Deep Learning to Replace Domain Knowledge,” in 25th IEEE Symposium on Computers and Communications (ISCC), July 2020

Christian Luebben

Christian Lübben is a research associate and PhD student at the chair of Network Architectures and Services at Technical University of Munich. Within the Internet of Things (IoT) Smart Space team (S2O) his research focus lies on optimizing IoT smart spaces using AI based advanced data analytics. The S2O team works on new ways of taming the complexity of the IoT. The goal is making a joint orchestration as simple as writing a smartphone App. Challenges include security, usability, resilience, scalability, and performance.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.