Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:


Thinking fast & slow: New DFKI project aims at making Deep Learning methods more reliable


When people face a problem, they can look at it calmly and logically, or they can decide spontaneously and emotionally. Modern computers are in a similar position: Thanks to their training with large amounts of data, Deep Learning methods can deliver fast, yet incomprehensible results.

Scientists of the German Research Center for Artificial Intelligence (DFKI) now investigate how these methods can be proven by formal procedures and thus become more reliable – without losing their speed. The new method will be tested by a juggling industrial robot. The project “Fast&Slow” is funded by the German Ministry for Education and Research (BMBF) with roughly 1.2 Million Euros.

A Pi4-Workerbot holds up two juggling balls.

DFKI GmbH, Photo: Lisa Jungmann

What is the better way to learn juggling: By watching and trying or by painstakingly planning each movement of the hand and each throw?

According to psychologist Daniel Kahneman, this example represents two systems that guide the process of human thinking – the fast, emotional and unconscious decision-making or its slow, logical and calculating counterpart.

Even though computers are still far from imitating the complexity of the human intellectual power, there are two similar procedures which Artificial Intelligence can use to make decisions.

While Deep Learning methods deliver fast, but rationally incomprehensible results, a formal calculation can lead to a verifiable and mathematically correct output – which, however, takes more time.

In a new project titled “Fast&Slow” that started on 1 November 2019, scientists of the DFKI are now investigating how these two methods could be combined. The Cyber-Physical Systems research department led by Prof. Dr. Rolf Drechsler aims at developing an Artificial Intelligence that can make both fast and reliable decisions.

Because Deep Learning methods within themselves only deliver sub-symbolically calculated results that are based on millions of parameters and enormous amounts of test examples.

However, this procedure does not meet the requirements for reliability and trustworthiness in many areas – for example when it comes to autonomous driving. For this reason, it is necessary to validate the results and train the AI with the correct output.

Method aims at helping robots to juggle and navigate safely

In order to make this possible, these sub-symbolical methods are meant to be combined with symbolical procedures, allowing the advantages of both – the speed as well as the comprehensible correctness of the results – to be used.

The first step towards this is defining problems that can be solved both formally as well as via Deep Learning algorithms. One example for this is the planning of actions. In the procedure, the AI is trained with the formally correct result, before attempting to solve the problem via the faster, sub-symbolical method. The new output can then be revised and, if necessary, corrected via the symbolical procedure.

The combination of the methods will be tested in two different experiments: In the first test procedure, so-called TurtleBots (small autonomous transport robots that are used for transport, inter alia) are meant to find a safe path through a Smart Home. In the second experiment, a Pi4-Workerbot – an industrial robot with two arms, is taught to juggle.

The aim is to allow the robot to juggle not only by itself but also together with people by knowing all necessary motion sequences and making quick decisions about the next movement via Deep Learning procedures.

Foundations for an unbiased and reliable AI

First of all however, the project “Fast&Slow” deals with the very basic problems of the two different methods: How can the information of two different AI methods be combined? What problems can be solved and verified formally, and in which situations is this verification of particular importance?

A common example for the weaknesses of Deep Learning are methods that create biases due to the data with which they have been trained. Especially in these kinds of situations, it is necessary to rely on formal results.

The scientists of the DFKI aim at developing the foundations for a safe and reliable implementation of Deep Learning methods in order to be able to use the potential of the decision-making processes even in more challenging areas.

For this reason, the German Ministry for Education and Science (BMBF) funds the project “Fast&Slow” with roughly 1.2 Million Euros over a period of three years.

At you may find photo material ready for download. You may use this material for your publication mentioning the source “DFKI GmbH, Photo: Lisa Jungmann”.

Prof. Dr. Dieter Hutter
German Research Center for Artificial Intelligence
Cyber-Physical Systems
Phone: +49 421 218 59831

Press contact:
German Research Center for Artificial Intelligence
Team Corporate Communications Bremen
Phone: +49 421 178 45 4180

Jens Peter Kückens DFKI Bremen | idw - Informationsdienst Wissenschaft

More articles from Information Technology:

nachricht Accelerating AI Together – DFKI Welcomes NVIDIA as Newest Shareholder
08.04.2020 | Deutsches Forschungszentrum für Künstliche Intelligenz GmbH, DFKI

nachricht Innovative Technologies for Satellites
07.04.2020 | Julius-Maximilians-Universität Würzburg

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: The human body as an electrical conductor, a new method of wireless power transfer

Published by Marc Tudela, Laura Becerra-Fajardo, Aracelys García-Moreno, Jesus Minguillon and Antoni Ivorra, in Access, the journal of the Institute of Electrical and Electronics Engineers

The project Electronic AXONs: wireless microstimulators based on electronic rectification of epidermically applied currents (eAXON, 2017-2022), funded by a...

Im Focus: Belle II yields the first results: In search of the Z′ boson

The Belle II experiment has been collecting data from physical measurements for about one year. After several years of rebuilding work, both the SuperKEKB electron–positron accelerator and the Belle II detector have been improved compared with their predecessors in order to achieve a 40-fold higher data rate.

Scientists at 12 institutes in Germany are involved in constructing and operating the detector, developing evaluation algorithms, and analyzing the data.

Im Focus: When ions rattle their cage

Electrolytes play a key role in many areas: They are crucial for the storage of energy in our body as well as in batteries. In order to release energy, ions - charged atoms - must move in a liquid such as water. Until now the precise mechanism by which they move through the atoms and molecules of the electrolyte has, however, remained largely unknown. Scientists at the Max Planck Institute for Polymer Research have now shown that the electrical resistance of an electrolyte, which is determined by the motion of ions, can be traced back to microscopic vibrations of these dissolved ions.

In chemistry, common table salt is also known as sodium chloride. If this salt is dissolved in water, sodium and chloride atoms dissolve as positively or...

Im Focus: Harnessing the rain for hydrovoltaics

Drops of water falling on or sliding over surfaces may leave behind traces of electrical charge, causing the drops to charge themselves. Scientists at the Max Planck Institute for Polymer Research (MPI-P) in Mainz have now begun a detailed investigation into this phenomenon that accompanies us in every-day life. They developed a method to quantify the charge generation and additionally created a theoretical model to aid understanding. According to the scientists, the observed effect could be a source of generated power and an important building block for understanding frictional electricity.

Water drops sliding over non-conducting surfaces can be found everywhere in our lives: From the dripping of a coffee machine, to a rinse in the shower, to an...

Im Focus: A sensational discovery: Traces of rainforests in West Antarctica

90 million-year-old forest soil provides unexpected evidence for exceptionally warm climate near the South Pole in the Cretaceous

An international team of researchers led by geoscientists from the Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research (AWI) have now...

All Focus news of the innovation-report >>>



Industry & Economy
Event News

Aachen Machine Tool Colloquium AWK'21 will take place on June 10 and 11, 2021

07.04.2020 | Event News

International Coral Reef Symposium in Bremen Postponed by a Year

06.04.2020 | Event News

13th AKL – International Laser Technology Congress: May 4–6, 2022 in Aachen – Laser Technology Live already this year!

02.04.2020 | Event News

Latest News

Doubts about basic assumption for the universe

08.04.2020 | Physics and Astronomy

Accelerating AI Together – DFKI Welcomes NVIDIA as Newest Shareholder

08.04.2020 | Information Technology

Ear’s inner secrets revealed with new technology

08.04.2020 | Medical Engineering

Science & Research
Overview of more VideoLinks >>>