Aug 202017

In order to achieve better brain signal transmission quality, the researchers apply contact gel. Photo: Michael Veit

Filtering information for search engines, acting as an opponent during a board game or recognizing images: Artificial intelligence has far outpaced human intelligence in certain tasks. Several groups from the Freiburg excellence cluster BrainLinks-BrainTools led by neuroscientist private lecturer Dr. Tonio Ball are showing how ideas from computer science could revolutionize brain research.

In the scientific journal “Human Brain Mapping” they illustrate how a self-learning algorithm decodes human brain signals that were measured by an electroencephalogram (EEG). It included performed movements, but also hand and foot movements that were merely thought or an imaginary rotation of objects. Even though the algorithm was not given any characteristics ahead of time, it works as quickly and precisely as traditional systems that have been created to solve certain tasks based on predetermined brain signal characteristics, which are therefore not appropriate for every situation. The demand for such diverse intersections between man and machine is huge: At the University Hospital Freiburg, for instance, it could be used for early detection of epileptic seizures. It could also be used to improve communication possibilities for severely paralyzed patients or an automatic neurological diagnosis.

“Our software is based on brain-inspired models that have proven to be most helpful to decode various natural signals such as phonetic sounds,” says computer scientist Robin Tibor Schirrmeister. The researcher is using it to rewrite methods that the team has used for decoding EEG data: So-called artificial neural networks are the heart of the current project at BrainLinks-BrainTools. “The great thing about the program is we needn’t predetermine any characteristics. The information is processed layer for layer, that is in multiple steps with the help of a non-linear function. The system learns to recognize and differentiate between certain behavioral patterns from various movements as it goes along,” explains Schirrmeister. The model is based on the connections between nerve cells in the human body in which electric signals from synapses are directed from cellular protuberances to the cell’s core and back again. “Theories have been in circulation for decades, but it wasn’t until the emergence of today’s computer processing power that the model has become feasible,” comments Schirrmeister.

Customarily, the model’s precision improves with a large number of processing layers. Up to 31 were used during the study, otherwise known as “Deep Learning”. Up until now, it had been problematic to interpret the network’s circuitry after the learning process had been completed. All algorithmic processes take place in the background and are invisible. That is why the researchers developed the software to create cards from which they could understand the decoding decisions. The researchers can insert new datasets into the system at any time. “Unlike the old method, we are now able to go directly to the raw signals that the EEG records from the brain. Our system is as precise, if not better, than the old one,” says head investigator Tonio Ball, summarizing the study’s research contribution. The technology’s potential has yet to be exhausted – together with his team, the researcher would like to further pursue its development: “Our vision for the future includes self-learning algorithms that can reliably and quickly recognize the user’s various intentions based on their brain signals. In addition, such algorithms could assist neurological diagnoses.”

Learn more: Artificial neural networks decode brain activity during performed and imagined movements


The Latest on: AI reads minds
  • What Your CEO Is Reading: Be Like Satya; AI Ethics; Equifax’s Board
    on September 22, 2017 at 9:36 am

    Every week, CIO Journal offers a glimpse into the mind of the CEO, whose view of technology is shaped by stories in management journals, general interest magazines and, of course, in-flight publications. Be like Satya. Microsoft Corp.’s chief executive ... […]

  • Why AI will need more emotional intelligence
    on September 22, 2017 at 3:10 am

    Part of the reason we don’t want to think too hard about EQ with bots is that there’s a bit of an “uncanny valley” for AI, that awkward gap where our minds essentially make ... If the bot doesn’t know how to read you, we won’t think of the ... […]

  • The 5 Levels of Meeting AI
    on September 21, 2017 at 10:57 am

    At first, AI meeting bots will reduce the cognitive load we put into ... and understand interpersonal and even company-wide dynamics. We’re not going to have mind-reading meeting bots tomorrow. The intelligence needs to evolve, through five broad stages ... […]

  • From AI to Blockchain to Data: Meet Ocean
    on September 21, 2017 at 6:27 am

    like the nature of the mind. For these reasons, AI was my first love. I started my AI reading and hacking intently in the early 90s. By 1997, I was far enough along hacking AI that people started paying me to do it. I never looked back, doing two ... […]

  • Unisys: Micro-segmentation and AI in the security wake of Equifax
    on September 20, 2017 at 11:51 am

    The Equifax security breach is on everyone's mind. Equifax has broken our trust and made clear ... of Equifax following a data breach impacting 143 million is galling. Read More Unisys traces its history back to 1873, with typewriters and adding machines ... […]

  • The AI robot that tells you how to VOTE: 'Nigel' learns about your preferences and recommends politicians with similar views
    on September 18, 2017 at 2:44 am

    These are general-purpose systems with intelligence comparable to that of the human mind. While this was the original goal of artificial intelligence, most AI research has turned ... is by this time next year to have Nigel read and write at a grade ... […]

  • AI can't replace the human mind says MRM Meteorite chief
    on September 14, 2017 at 9:00 am

    The mind will be challenged by AI but I don't think it can be a substitute. On the print side, people still read magazines and newspapers, maybe not as many but we still do. What should be happening is making sure that print is a part of the story and not ... […]

  • Future of AI in Social Media
    on September 14, 2017 at 12:14 am

    Popular Read: 5 Reasons Why Organizations Struggle To Adopt CI and CD For social media, this means AI can provide aid with anything from ... Machine learning isn’t the first thing that comes to one’s mind. Pinterest has evolved from a mere bookmarking ... […]

  • Three trends to keep top of mind when crafting an AI strategy
    on September 12, 2017 at 10:01 pm

    You also agree that your personal information may be transferred and processed in the United States, and that you have read and agree to the Terms ... laying out three trends CIOs should keep in mind when crafting an AI strategy. New interfaces will ... […]

  • Mind-reading AI is the newest defense against cyber attacks
    on September 12, 2017 at 10:57 am

    Ransomware has been disastrous for businesses and individuals alike, with recent attacks like WannaCry costing companies millions, and personal attacks threatening private data. We’re all at risk. Criminals are holding data and information hostage using ... […]

via Google News and Bing News

Leave a Reply

%d bloggers like this: