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 Smart machine maintenance: New AI system also detects unknown faults
25.05.2020 | Universität des Saarlandes

nachricht Artificial Intelligence for optimized mobile communication
25.05.2020 | Fraunhofer-Institut für Angewandte Festkörperphysik IAF

All articles from Information Technology >>>

The most recent press releases about innovation >>>

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

Im Focus: I-call - When microimplants communicate with each other / Innovation driver digitization - "Smart Health“

Microelectronics as a key technology enables numerous innovations in the field of intelligent medical technology. The Fraunhofer Institute for Biomedical Engineering IBMT coordinates the BMBF cooperative project "I-call" realizing the first electronic system for ultrasound-based, safe and interference-resistant data transmission between implants in the human body.

When microelectronic systems are used for medical applications, they have to meet high requirements in terms of biocompatibility, reliability, energy...

Im Focus: When predictions of theoretical chemists become reality

Thomas Heine, Professor of Theoretical Chemistry at TU Dresden, together with his team, first predicted a topological 2D polymer in 2019. Only one year later, an international team led by Italian researchers was able to synthesize these materials and experimentally prove their topological properties. For the renowned journal Nature Materials, this was the occasion to invite Thomas Heine to a News and Views article, which was published this week. Under the title "Making 2D Topological Polymers a reality" Prof. Heine describes how his theory became a reality.

Ultrathin materials are extremely interesting as building blocks for next generation nano electronic devices, as it is much easier to make circuits and other...

Im Focus: Rolling into the deep

Scientists took a leukocyte as the blueprint and developed a microrobot that has the size, shape and moving capabilities of a white blood cell. Simulating a blood vessel in a laboratory setting, they succeeded in magnetically navigating the ball-shaped microroller through this dynamic and dense environment. The drug-delivery vehicle withstood the simulated blood flow, pushing the developments in targeted drug delivery a step further: inside the body, there is no better access route to all tissues and organs than the circulatory system. A robot that could actually travel through this finely woven web would revolutionize the minimally-invasive treatment of illnesses.

A team of scientists from the Max Planck Institute for Intelligent Systems (MPI-IS) in Stuttgart invented a tiny microrobot that resembles a white blood cell...

Im Focus: NASA's Curiosity rover finds clues to chilly ancient Mars buried in rocks

By studying the chemical elements on Mars today -- including carbon and oxygen -- scientists can work backwards to piece together the history of a planet that once had the conditions necessary to support life.

Weaving this story, element by element, from roughly 140 million miles (225 million kilometers) away is a painstaking process. But scientists aren't the type...

Im Focus: Making quantum 'waves' in ultrathin materials

Study co-led by Berkeley Lab reveals how wavelike plasmons could power up a new class of sensing and photochemical technologies at the nanoscale

Wavelike, collective oscillations of electrons known as "plasmons" are very important for determining the optical and electronic properties of metals.

All Focus news of the innovation-report >>>



Industry & Economy
Event News

Dresden Nexus Conference 2020: Same Time, Virtual Format, Registration Opened

19.05.2020 | 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

Latest News

Inexpensive retinal diagnostics via smartphone

25.05.2020 | Medical Engineering

Smart machine maintenance: New AI system also detects unknown faults

25.05.2020 | Information Technology

Artificial Intelligence for optimized mobile communication

25.05.2020 | Information Technology

Science & Research
Overview of more VideoLinks >>>