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
  • Video shows what happens when a robot conducts an Italian orchestra
    on September 18, 2017 at 5:53 pm

    The robot made its debut at a charity concert at the historic ... "YuMi demonstrated how intuitive, how self-learning this machine is - how wonderful our software really is in learning the movement of a conductor, sensing the music and really conducting ... […]

  • Who is liable when robots and AI get it wrong?
    on September 18, 2017 at 11:18 am

    The manufacturer, developer, the person controlling it, or the robot itself? Or is it a matter of allocating and apportioning risk and liability? As autonomy and self-learning capabilities increase, robots and intelligent AI systems will feel less and less ... […]

  • These are the new technologies Americans fear most
    on September 18, 2017 at 2:45 am

    Among respondents, women were more concerned than men about every category of technology except for self-learning computers and robots that teach each other. Men were slightly more concerned about bot of these technologies. Millennial respondents were ... […]

  • Robotics, robots and technology: a simplified overview of a vast subject
    on September 17, 2017 at 12:08 am

    The second is that robots are able to process sensory data in order to make ... This perception is being challenged by self-learning structures, such as the neural network used for machine learning. In these cases the intelligence is not programmed but ... […]

  • What’s beyond continuous testing? AI
    on September 15, 2017 at 1:00 am

    From the golden robots of Hephaestus, to Dr. Frankenstein’s monster ... Forrester defines AI as “A system, built through coding, business rules, and increasingly self-learning capabilities, that is able to supplement human cognition and activities ... […]

  • Watch: YuMi the robot breaks a barrier by conducting Western classical music performances in Italy
    on September 15, 2017 at 12:32 am

    “YuMi demonstrated how intuitive, how self-learning this machine is.” The robot learnt in two steps. The first step involved capturing the movements of Andrea Colombini, the director of the Lucca Philharmonic Orchestra, during rehearsals using a ... […]

  • Swiss robot conducts orchestra in Italy
    on September 14, 2017 at 7:06 am

    14 (UPI) --A robot took the stage at a charity concert in Italy to ... "YuMi demonstrated how intuitive, how self-learning this machine is - how wonderful our software really is in learning the movement of a conductor, sensing the music, and really ... […]

  • Robot YuMi celebrates conducting debut with Andrea Bocelli
    on September 13, 2017 at 10:49 pm

    ABB's dual-arm robot made took the stage with Italian tenor Andrea Bocelli ... "YuMi demonstrated how intuitive, how self-learning this machine is – how wonderful our software really is in learning the movement of a conductor, sensing the music, and ... […]

  • A robot conductor led a live orchestra performance
    on September 13, 2017 at 1:12 pm

    Do robots need a heart to complete tasks of passion ... "YuMi demonstrated how intuitive, how self-learning this machine is -- how wonderful our software really is in learning the movement of a conductor, sensing the music, and really conducting an ... […]

  • IBM’s Watson AI is learning to understand nuance and context
    on September 10, 2017 at 2:01 pm

    They are self-learning and train on an incremental basis ... person is upset probably isn’t going to be passing the Turing Test any time soon – but the robot who does will trace its family tree back to one like Watson. […]

via Google News and Bing News

Other Interesting Posts

Leave a Reply

%d bloggers like this: