A research team at MIT developed software, called TextFooler, which looked for words which were most crucial to an NLP classifier and replaced them. The team offered an example:

“The characters, cast in impossibly contrived situations, are totally estranged from reality”, and
“The characters, cast in impossibly engineered circumstances, are fully estranged from reality”

No problem for a human to decipher. Yet the results on the AIs were startling. For instance BERT, Google’s neural net, was worse by a factor of up to seven at identifying whether reviews on Yelp were positive or negative.

Douglas Heaven, writing a roundup of the study for MIT Technology Review, explained why the research was important. “We have seen many examples of adversarial attacks, most often with image recognition systems, where tiny alterations to the input can flummox an AI and make it misclassify what it sees,” Heaven wrote. “TextFooler shows that this style of attack also breaks NLP, the AI behind virtual assistants – such as Siri, Alexa and Google Home – as well as other language classifiers like spam filters and hate-speech detectors.”

This publication has explored various methods where AI technologies are outstripping human efforts, such as detecting breast cancer, playing StarCraft, and public debating. In other fields, resistance – however futile – remains. In December it was reported that human drivers were still overall beating AIs at drone racing, although the chief technology officer of the Drone Race League predicted that 2023 would be the year where AI took over.

The end goal for software such as TextFooler, the researchers hope, is to make NLP systems more robust.

Postscript: For those reading from outside the British Isles, China, and certain Commonwealth countries – to ‘snooker’ someone, deriving from the sport of the same name, is to ‘leave one in a difficult position.’ The US equivalent is ‘behind the eight-ball’, although that would have of course thrown the headline out.

The post MIT software shows how NLP systems are snookered by simple synonyms appeared first on AI News.

Good sleep is vital for our mental and physical wellbeing. Diagnosing problems today, however, can be difficult as it requires patients to be fitted with electrodes and various sensors.

The researchers from MIT and Massachusetts General Hospital used an AI algorithm to analyse radio signals around a subject. These readings are translated into the stages of sleep: awake, light, deep, or rapid eye movement.

“Imagine if your WiFi router knows when you are dreaming and can monitor whether you are having enough deep sleep, which is necessary for memory consolidation,” says Dina Katabi, the Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science, who led the study. “Our vision is developing health sensors that will disappear into the background and capture physiological signals and important health metrics, without asking the user to change her behavior in any way.”

There are possible applications for utilising this data beyond healthcare. For example, all the lights in a home could switch off automatically when occupants fall asleep to conserve energy. If occupants wake in the night to use the bathroom, certain lights could be switched on to guide the way.

With more than 50 million current (known) sufferers of sleep disorders in America alone, this research could be groundbreaking. It will help to diagnose and monitor problems without cumbersome and expensive specialist equipment.

“The opportunity is very big because we don’t understand sleep well, and a high fraction of the population has sleep problems,” says Mingmin Zhao, an MIT graduate and the paper’s first author. “We have this technology that, if we can make it work, can move us from a world where we do sleep studies once every few months in the sleep lab to continuous sleep studies in the home.”

Katabi and Zhao worked on the study with Matt Bianchi, chief of the division of sleep medicine at MGH, and Tommi Jaakkola, the Thomas Siebel Professor of Electrical Engineering and Computer Science and a member of the Institute for Data, Systems, and Society at MIT, and Shichao Yue, another MIT graduate student who is also a co-author on the paper.

AI beyond sleep disorders

Some of Katabi’s previous work alongside her fellow researchers at MIT also made use of radio waves. One laptop-sized box, which emits low-power RF signals, revealed vital signs including pulse and breathing rate. This could be used to monitor the elderly to alert medical professionals of worrying changes to their vitals.

Artificial intelligence using deep neural networks has made all of this possible. Extracting relevant information from the large datasets while removing erroneous results required the researchers to build their own algorithm.

“Our device allows you not only to remove all of these sensors that you put on the person and make it a much better experience that can be done at home, it also makes the job of the doctor and the sleep technologist much easier,” Katabi says. “They don’t have to go through the data and manually label it.”

The researchers will present their new sensor at the International Conference on Machine Learning on August 9th, 2017.

What health applications are you excited to see AI used for?

The post AI uses radio waves to diagnose sleep disorders appeared first on AI News.