Project

Fast&Slow

Combination of Symbolic and Subsymbolic Methods

Deep learning methods are used in many application areas and work very efficiently after a training phase. However, in general no reliable statement can be made about their correctness. In contrast, the correctness of analytical, plan-based or deductive algorithms can be verified with proven methods, but they are often too slow in application.

The project Fast&Slow investigates a systematic combination of both methods, in which the symbolic method trains the subsymbolic method and monitors its operation. The developed methodology will be validated in two extensive case studies in the areas of action planning in a smart home and trajectory planning for a two-arm robot.

The approach of combining the verifiability of symbolic approaches with the efficiency of sub-symbolic procedures can be applied in many application domains, since lack of verification is an acute obstacle to the use of deep learning techniques in safety-relevant areas such as autonomous driving.

Sponsors

BMBF - Federal Ministry of Education and Research

01IS19072

BMBF - Federal Ministry of Education and Research

Share project:

Contact Person

Keyfacts

Publications about the project

Udo Frese, Arne Hasselbring, Thomas Röfer, Johannes Hackbarth

In: Giuseppina Gini, Henk Nijmeijer, Wolfram Burgard, Dimitar Filev (editor). Proceedings of the 19th International Conference on Informatics in Control, Automation and Robotics. International Conference on Informatics in Control, Automation and Robotics (ICINCO-2022) July 14-16 Lisbon Portugal Pages 201-208 SCITEPRESS 2022.

To the publication

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz