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: Towards a better understanding of the underlying mechanisms
The automatic identification of complex features in images has already become reality thanks to artificial neural networks.
Using artificial intelligence to analyze placentas
A team of researchers has developed a novel solution that could produce accurate, automated and near-immediate placental diagnostic reports through computerized photographic image analysis.
How artificial intelligence can transform psychiatry
Scientists have developed a new mobile app that categorizes mental health status based on speech patterns.
Artificial intelligence system gives fashion advice
A University of Texas at Austin-led computer science team has developed an artificial intelligence system that can look at a photo of an outfit and suggest helpful tips to make it more fashionable.
Artificial intelligence improves biomedical imaging
ETH researchers use artificial intelligence to improve quality of images recorded by a relatively new biomedical imaging method.
Uncovering hidden intelligence of collectives
Research team including scientists from Konstanz discovers that information processing in animal groups occurs not only in the brains of animals but also in their social network.
Evolution of learning is key to better artificial intelligence
Researchers at Michigan State University say that true, human-level intelligence remains a long way off, but their new paper published in The American Naturalist explores how computers could begin to evolve learning in the same way as natural organisms did -- with implications for many fields, including artificial intelligence.
The brain inspires a new type of artificial intelligence
Using advanced experiments on neuronal cultures and large scale simulations, scientists at Bar-Ilan University have demonstrated a new type of ultrafast artifical intelligence algorithms -- based on the very slow brain dynamics -- which outperform learning rates achieved to date by state-of-the-art learning algorithms.
Can videogames promote emotional intelligence in teenagers?
A new study has shown that videogames, when used as part of an emotional intelligence training program, can help teenagers evaluate, express, and manage their own emotions immediately after the training.
'Artificial intelligence' fit to monitor volcanoes
More than half of the world's active volcanoes are not monitored instrumentally.
More Intelligence News and Intelligence Current Events

Top Science Podcasts

We have hand picked the top science podcasts of 2019.
Now Playing: TED Radio Hour

Accessing Better Health
Essential health care is a right, not a privilege ... or is it? This hour, TED speakers explore how we can give everyone access to a healthier way of life, despite who you are or where you live. Guests include physician Raj Panjabi, former NYC health commissioner Mary Bassett, researcher Michael Hendryx, and neuroscientist Rachel Wurzman.
Now Playing: Science for the People

#544 Prosperity Without Growth
The societies we live in are organised around growth, objects, and driving forward a constantly expanding economy as benchmarks of success and prosperity. But this growing consumption at all costs is at odds with our understanding of what our planet can support. How do we lower the environmental impact of economic activity? How do we redefine success and prosperity separate from GDP, which politicians and governments have focused on for decades? We speak with ecological economist Tim Jackson, Professor of Sustainable Development at the University of Surrey, Director of the Centre for the Understanding of Sustainable Propserity, and author of...
Now Playing: Radiolab

An Announcement from Radiolab