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 The Drone Industry Evolve In 2018
    on February 16, 2018 at 1:32 pm

    Elon Musk also called out on the ban on killer robots which can also include drones ... current technologies need to be adapted to allow for autonomous navigation and self-learning capabilities. Drones have evolved remarkably in the last decade or two. […]

  • How will artificial intelligence impact UK consumers lives?
    on February 15, 2018 at 4:05 am

    The introduction of robots and AI will offer an opportunity to revolutionise this interaction process.” “Cognitive systems are self-learning systems that simulate the way a brain works using data mining, analytics and natural language processing to ... […]

  • How Data Scientists Are Wasting Their Time
    on February 12, 2018 at 12:00 am

    There is a consensus among many that A.I. trumps human ability every time when it comes to data collection, correlation, and bucketing; perpetual self-learning and algorithm ... Data Scientists Bow Out and Let the Robots Take Over? We may want our data ... […]

  • How AI Is Changing the Retail Industry
    on February 12, 2018 at 12:00 am

    In-store robots could take some jobs but also create others ... gender and other variables by using self-learning algorithms could take what once was a lost customer and make their experience far more intimate, targeted and effective. […]

  • The Age of the machines ( Artificial Intelligence )
    on February 11, 2018 at 5:53 am

    School student: Why was the Robot dismantled? Chitti ... A computer can only do tasks based on programmed data. Self-learning systems are not autonomous and cannot multi-task. For example, a computer programmed to translate French into English cannot ... […]

  • VISION and the Machine Vision Industry on a Growth Path
    on February 7, 2018 at 4:00 pm

    In machine vision it is therefore possible, for example, to integrate intelligent camera modules in machines or robots, thus making them an indispensable ... Unlike current processes, these self-learning systems are taught a large number of images and ... […]

  • Heavy Duty Industrial Robot Market Growth Boosted by Low Component Price | Technavio
    on December 14, 2017 at 4:00 pm

    The global heavy duty industrial robot market has witnessed several developments in the recent years, with the integration of advanced technologies and features such as self-learning, compact, mounting, high speed, and collaborative robots. As the ... […]

  • Robots will run mines within the next decade, Anglo says
    on November 29, 2017 at 3:28 pm

    Some mines in the next decade will run without humans and instead rely on robots, virtual models and sensors ... O’Neill said. Small and self-learning, the technology requires less infrastructure than current methods, and commercial application is ... […]

  • Elon Musk isn’t worried about killer robots, he’s worried about the development of unregulated, self-learning Super AI
    on November 28, 2017 at 3:46 am

    Naysayers and doomsday heralds aren’t in short supply in this world and are largely ignored by the “saner” populace. Unfortunately, when one of the said heralds turns out to be of the likes of Tony Stark-esque Elon Musk, it’s in our best interest ... […]

via Google News and Bing News

Other Interesting Posts

Leave a Reply

%d bloggers like this: