Aug 222017
 

via Learning Mind

New stochastic separation theorems proved by University of Leicester mathematicians could enhance capabilities of artificial intelligence

Errors in Artificial Intelligence which would normally take a considerable amount of time to resolve could be corrected immediately with the help of new research from the University of Leicester.

Researchers from the University of Leicester’s Department of Mathematics have published a paper [1] in the journal Neural Networks outlining mathematical foundations for new algorithms which could allow for Artificial Intelligence to collect error reports and correct them immediately without affecting existing skills – at the same time accumulating corrections which could be used for future versions or updates.

This could essentially provide robots with the ability to correct errors instantaneously, effectively ‘learn’ from their mistakes without damage to the knowledge already gained, and ultimately spread new knowledge amongst themselves.

Together with Industrial partners from ARM, the algorithms are combined into a system, an AI corrector, capable of improving performance of legacy AIs on-the-fly (the technical report is available online [2]).

ARM is the world’s largest provider of semiconductor IP and is the architecture of choice for more than 90% of the smart electronic products being designed today.

Professor Alexander Gorban from the University of Leicester’s Department of Mathematics said: “Multiple versions of Artificial Intelligence Big Data analytics systems have been deployed to date on millions of computers and gadgets across various platforms. They are functioning in non-uniform networks and interact.

“Industrial technological giants such as Amazon, IBM, Google, Facebook, SoftBank, ARM and many others are involved in the development of these systems. Performance of them increases, but sometimes they make mistakes like false alarms, misdetections, or wrong predictions. The mistakes are unavoidable because inherent uncertainty of Big Data.

“It seems to be very natural that humans can learn from their mistakes immediately and do not repeat them (at least, the best of us). It is a big problem how to equip Artificial Intelligence with this ability.

“It is difficult to correct a large AI system on the fly, more difficult as to shoe a horse at full gallop without stopping.

“We have recently found that a solution to this issue is possible. In this work, we demonstrate that in high dimensions and even for exponentially large samples, linear classifiers in their classical Fisher’s form are powerful enough to separate errors from correct responses with high probability and to provide efficient solution to the non-destructive corrector problem.”

There is a desperate need in a cheap, fast and local correction procedure that does not damage important skills of the AI systems in the course of correction.

Iterative methods of machine learning are never cheap for Big Data and huge AI systems and therefore the researchers suggest that the corrector should be non-iterative with the reversible correctors needed to reconfigure and merge local corrections.

Dr Ivan Tyukin from the University of Leicester’s Department of Mathematics said: “It is often infeasible just to re-train the systems for several reasons: they are huge and re-training requires significant computational resources or long time or both; it may be impossible retrain the system locally, at the point where mistake occur; and we can fix one thing but break another leading to that important skills could vanish.

“The development of sustainable large intelligent systems for mining of Big Data requires creation of technology and methods for fast non-destructive, non-iterative, and reversible corrections. No such technology existed until now.”

The researchers have discovered and proved stochastic separation theorems which provide tools for correction of the large intelligent data analytic systems.

With this approach, instantaneous learning in Artificial Intelligence could be possible, providing AI with the ability to re-learn following a mistake after an error has occurred.

Learn more: New theorems help robots to correct errors on-the-fly and learn from each other

 

The Latest on: Self-learning robots
  • How Cognitive Intelligence can drive banks’ cost income breakthroughs
    on November 20, 2017 at 9:24 pm

    And this type of solution becomes even better with the self-learning character of the machine learning software ... But also on the cost side this kind of predictive robots will seriously drive further cost reductions. The applications of robot process ... […]

  • 5 things CFOs need to consider to survive the 4th industrial revolution
    on November 20, 2017 at 10:52 am

    We all studied the 1 st industrial revolution, we all have experienced the 3 rd industrial revolution, the digital revolution and now we are at the beginning of the 4 th industrial revolution, with artificial intelligence, robots, cloud solutions ... […]

  • PR: Mirocana Predicts Financial Markets. Your Key to Success on Stock, Currency and Crypto-Currency Markets
    on November 19, 2017 at 1:30 am

    Of the companies competitive advantages George Petrov, Mirocana CEO said: “Our goal is to solve the problems of personal investing with a trader, introducing a constantly self-learning AI that ... and AI-powered trading robots are no longer available ... […]

  • Lego robotics for kids now in Kathmandu
    on November 18, 2017 at 10:38 pm

    and deploy their robots to accomplish various challenges. “The event is an important step towards meeting our vision and objectives where we intend to cultivate a keen sense of self-learning, problem solving skills, and critical thinking,” said Saral ... […]

  • UN triggers talks on killer robots but haze persists
    on November 18, 2017 at 12:00 am

    Some of those include industrial robots that cause job losses and very smart go-it ... simply because it is guided by on-the-go self-learning or programmed artificial intelligence capabilities. Recognizing the importance of such questions, the new group ... […]

  • Chinese robot scores high in doctor qualification test
    on November 7, 2017 at 7:54 pm

    The whole process was recorded to prevent cheating, according to iFlytek. The test showed the robot has mastered self-learning and problem solving abilities to a degree. It will be used to assist doctors in clinical diagnosis and will see patients in ... […]

  • Robot Scores High Result on National Doctor Qualification Test
    on November 7, 2017 at 4:30 pm

    The robot, co-developed by leading Chinese tech firm iFlytek ... The test showed the robotic doctor has mastered self-learning and problem solving abilities to a degree. It will be used to assist doctors in clinical diagnosis and will see patients in ... […]

  • Close your bunker and put away the canned goods, a bot-pocalypse isn’t going to happen
    on November 7, 2017 at 6:40 am

    Robots will take over the world ... Data and machine learning are used to create self-learning systems that can automate simple tasks, but they cannot think for themselves. For example, earlier this year, Google revealed its AutoML project, in which ... […]

  • Self-learning robot hands
    on June 8, 2017 at 7:50 am

    The system was developed as part of the large-scale research project Famula at Bielefeld University's Cluster of Excellence Cognitive Interaction Technology (CITEC). The knowledge gained from this project could contribute to future service robots, for ... […]

  • Intel Inside $599 Home Robots
    on June 3, 2016 at 6:39 am

    Cheap $599 home robots like the Asustek Zenbo are going to be the Intel ... Intel investors should really fall in love with the Zenbo. This affordable $599 self-learning robot will save the Atom product line. It will also help sell more Intel-made ... […]

via Google News and Bing News

Other Interesting Posts

Leave a Reply

%d bloggers like this: