Nav: Home

How intelligent is artificial intelligence?

March 12, 2019

Artificial Intelligence (AI) and machine learning algorithms such as Deep Learning have become integral parts of our daily lives: they enable digital speech assistants or translation services, improve medical diagnostics and are an indispensable part of future technologies such as autonomous driving. Based on an ever increasing amount of data and powerful novel computer architectures, learning algorithms appear to reach human capabilities, sometimes even excelling beyond. The issue: so far it often remains unknown to users, how exactly AI systems reach their conclusions. Therefore it may often remain unclear, whether the AI's decision making behavior is truly 'intelligent' or whether the procedures are just averagely successful.

Researchers from TU Berlin, Fraunhofer Heinrich Hertz Institute HHI and Singapore University of Technology and Design (SUTD) have tackled this question and have provided a glimpse into the diverse "intelligence" spectrum observed in current AI systems, specifically analyzing these AI systems with a novel technology that allows automatized analysis and quantification.

The most important prerequisite for this novel technology is a method developed earlier by TU Berlin and Fraunhofer HHI, the so-called Layer-wise Relevance Propagation (LRP) algorithm that allows visualizing according to which input variables AI systems make their decisions. Extending LRP, the novel Spectral relevance analysis (SpRAy) can identify and quantify a wide spectrum of learned decision making behavior. In this manner it has now become possible to detect undesirable decision making even in very large data sets.

This so-called 'explainable AI' has been one of the most important steps towards a practical application of AI, according to Dr. Klaus-Robert Müller, Professor for Machine Learning at TU Berlin. "Specifically in medical diagnosis or in safety-critical systems, no AI systems that employ flaky or even cheating problem solving strategies should be used."

By using their newly developed algorithms, researchers are finally able to put any existing AI system to a test and also derive quantitative information about them: a whole spectrum starting from naive problem solving behavior, to cheating strategies up to highly elaborate "intelligent" strategic solutions is observed.

Dr. Wojciech Samek, group leader at Fraunhofer HHI said: "We were very surprised by the wide range of learned problem-solving strategies. Even modern AI systems have not always found a solution that appears meaningful from a human perspective, but sometimes used so-called 'Clever Hans Strategies'."

Clever Hans was a horse that could supposedly count and was considered a scientific sensation during the 1900s. As it was discovered later, Hans did not master math but in about 90 percent of the cases, he was able to derive the correct answer from the questioner's reaction.

The team around Klaus-Robert Müller and Wojciech Samek also discovered similar "Clever Hans" strategies in various AI systems. For example, an AI system that won several international image classification competitions a few years ago pursued a strategy that can be considered naïve from a human's point of view. It classified images mainly on the basis of context. Images were assigned to the category "ship" when there was a lot of water in the picture. Other images were classified as "train" if rails were present. Still other pictures were assigned the correct category by their copyright watermark. The real task, namely to detect the concepts of ships or trains, was therefore not solved by this AI system - even if it indeed classified the majority of images correctly.

The researchers were also able to find these types of faulty problem-solving strategies in some of the state-of-the-art AI algorithms, the so-called deep neural networks - algorithms that were so far considered immune against such lapses. These networks based their classification decision in part on artifacts that were created during the preparation of the images and have nothing to do with the actual image content.

"Such AI systems are not useful in practice. Their use in medical diagnostics or in safety-critical areas would even entail enormous dangers," said Klaus-Robert Müller. "It is quite conceivable that about half of the AI systems currently in use implicitly or explicitly rely on such 'Clever Hans' strategies. It's time to systematically check that, so that secure AI systems can be developed."

With their new technology, the researchers also identified AI systems that have unexpectedly learned "smart" strategies. Examples include systems that have learned to play the Atari games Breakout and Pinball. "Here the AI clearly understood the concept of the game and found an intelligent way to collect a lot of points in a targeted and low-risk manner. The system sometimes even intervenes in ways that a real player would not," said Wojciech Samek.

"Beyond understanding AI strategies, our work establishes the usability of explainable AI for iterative dataset design, namely for removing artefacts in a dataset which would cause an AI to learn flawed strategies, as well as helping to decide which unlabeled examples need to be annotated and added so that failures of an AI system can be reduced," said SUTD Assistant Professor Alexander Binder.

"Our automated technology is open source and available to all scientists. We see our work as an important first step in making AI systems more robust, explainable and secure in the future, and more will have to follow. This is an essential prerequisite for general use of AI," said Klaus-Robert Müller.
-end-


Singapore University of Technology and Design

Related Intelligence Articles:

Artificial intelligence predicts patient lifespans
A computer's ability to predict a patient's lifespan simply by looking at images of their organs is a step closer to becoming a reality, thanks to new research led by the University of Adelaide.
Scientists find new genetic roots for intelligence
An international research team led by Professor Danielle Posthuma from the Vrije Universiteit Amsterdam, The Netherlands, has made a major advance in understanding the genetic underpinnings of intelligence.
Artificial intelligence may help diagnose tuberculosis in remote areas
Researchers are training artificial intelligence models to identify tuberculosis (TB) on chest X-rays, which may help screening and evaluation efforts in TB-prevalent areas with limited access to radiologists, according to a new study.
Emotional intelligence helps make better doctors
A study found that pediatric residents had a median score of 110 on an emotional intelligence survey, compared to an average score of 100 in the general population.
Conformity is not a universal indicator of intelligence in children, study says
Because innovation is part of the American culture, adults in the United States may be less likely to associate children's conformity with intelligence than adults from other populations, according to research from developmental psychologists at the University of Texas at Austin.
Artificial intelligence in quantum systems, too
The UPV/EHU's Department of Physical Chemistry has conducted world-class research in physics and quantum computation.
Artificial intelligence enters the nutraceutical industry
Life Extension (LE) launched a new line of nutraceuticals called GEROPROTECTTM, and the first product in the series called Ageless Cell combines some of the natural compounds that were shortlisted by Insilico Medicine's algorithms and are generally recognized as safe (GRAS).
Dogs, toddlers show similarities in social intelligence
University of Arizona researcher Evan MacLean, director of the Arizona Canine Cognition Center, found that dogs and 2-year-old children show similar patterns in social intelligence, much more so than human children and one of their closest relatives: chimpanzees.
The world's first demonstration of spintronics-based artificial intelligence
Researchers at Tohoku University have, for the first time, successfully demonstrated the basic operation of spintronics-based artificial intelligence.
Artificial intelligence to predict odors
FAU chemists are developing an artificial intelligence application which can predict which molecule structures will produce or suppress specific odors.

Related Intelligence Reading:

Best Science Podcasts 2019

We have hand picked the best science podcasts for 2019. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Anthropomorphic
Do animals grieve? Do they have language or consciousness? For a long time, scientists resisted the urge to look for human qualities in animals. This hour, TED speakers explore how that is changing. Guests include biological anthropologist Barbara King, dolphin researcher Denise Herzing, primatologist Frans de Waal, and ecologist Carl Safina.
Now Playing: Science for the People

#SB2 2019 Science Birthday Minisode: Mary Golda Ross
Our second annual Science Birthday is here, and this year we celebrate the wonderful Mary Golda Ross, born 9 August 1908. She died in 2008 at age 99, but left a lasting mark on the science of rocketry and space exploration as an early woman in engineering, and one of the first Native Americans in engineering. Join Rachelle and Bethany for this very special birthday minisode celebrating Mary and her achievements. Thanks to our Patreons who make this show possible! Read more about Mary G. Ross: Interview with Mary Ross on Lash Publications International, by Laurel Sheppard Meet Mary Golda...