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.
Learn more: How intelligent is artificial intelligence?
The Latest on: Artificial intelligence
via Google News
The Latest on: Artificial intelligence
- New York City wants to restrict artificial intelligence in hiringon November 20, 2020 at 1:08 pm
New York City is trying to rein in the use of algorithms used to screen job applicants. It's one of the first cities in the U.S. to try to regulate what is an increasingly common — and opaque — hiring ...
- Time may be right for professionalizing artificial intelligence practiceson November 20, 2020 at 8:30 am
"It's unlikely that you'd trust a 'citizen architect' to build your home in the same way that you wouldn't visit a 'citizen doctor' when you get sick." ...
- Can artificial intelligence give elephants a winning edge?on November 20, 2020 at 8:06 am
With great technology, collaboration and a commitment to stop the Ivory trade that leads to most elephant deaths, there’s a real chance to save these singular creatures.
- Artificial intelligence could be used to hack connected cars, drones warn security expertson November 20, 2020 at 4:46 am
Cyberattacks on vulnerabilities in connected vehicles could have very real physical consequences if security isn't managed properly.
- Unlock The Full Potential Of Artificial Intelligenceon November 20, 2020 at 3:05 am
The past year has been a learning experience for all of us, and collectively we’ve managed incredible things. Out of necessity, organizations have massively increased their speed of digitization and ...
- Artificial intelligence and satellite technologies reveal detailed map of air pollution across UKon November 20, 2020 at 1:00 am
A novel method that combines artificial intelligence with remote sensing satellite technologies has produced the most detailed coverage of air pollution in Britain to date.
- Artificial intelligence-based tool may help diagnose opioid addiction earlieron November 19, 2020 at 6:13 pm
Researchers have used machine learning, a type of artificial intelligence, to develop a prediction model for the early diagnosis of opioid use disorder.
- Artificial Intelligence in Drug Discovery Market Size, Share to Witness Unprecedented Growth Through 2027-Industry Newson November 19, 2020 at 2:11 pm
Global Artificial Intelligence in Drug Discovery Market is valued approximately at USD 259 million in 2019 and is anticipated to grow at a CAGR of 40.80% over the forecast period 2020-2027. Request ...
- Artificial Intelligence (AI) in Drug Discovery Market anticipated to grow with a healthy growth rate of more than 40.7% by 2026on November 19, 2020 at 7:42 am
Global Artificial Intelligence (AI) in Drug Discovery Market is valued approximately at USD 260 million in 2019 and is anticipated to grow with a healthy growth rate of more than 40.7% over the ...
- Artificial Intelligence Chip Market CAGR to Reach 35% During 2019 to 2027on November 18, 2020 at 4:43 am
Pune, New York, USA, November 18 2020 (Wiredrelease) Research Dive :The global artificial intelligence chip market was valued at US$ 5,658.1 Mn in 2018 and is expected to reach US$ 83,252.7 Mn by 2027 ...
via Bing News