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  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 ).
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.
The Latest on: Self-learning robots
- Covid-19 Devastated Some Industries But Accelerated AI Use By Companies Across The Countryon April 26, 2021 at 3:42 am
Even as applications of machine learning and perception platforms become commonplace, a thick layer of hype and fuzzy jargon clings to AI-enabled software.That makes it tough to identify the most ...
- Israeli-Made Robots Are Powering the E-Commerce Revolutionon April 25, 2021 at 9:53 am
and robots so that they arrive where they’re needed at the precise time that they’re needed in the most efficient way possible. “It’ll blow your mind even more when you realize that it is also a ...
- UiPath: Automation Is Not Automatic Appealon April 24, 2021 at 7:20 am
UiPath has seen huge growth in recent years accompanied by great operating leverage. The appeal is hard to see given the current valuations, but the potential is certainly there.
- AI Eye Podcast - Baidu Unveils Intelligent Driving And Cloud Upgrades At Auto Shanghai 2021, Unity Software Announces Unity Computer Vision Datasetson April 19, 2021 at 11:08 am
With the big data cloud solution, Apollo will work with car companies on a closed loop for self-learning in a smart ... discover new applications." Smart Robots Market Has Potential to Grow ...
- Domino's, Nuro to start robot pizza delivery in Houstonon April 12, 2021 at 4:12 am
With a small, low-speed vehicle to carry packages instead of people, the robot company has been pulling ahead of other autonomous startups in gaining regulatory approvals for on-road vehicle ...
- Hanover Fair: Where humans meet machineson April 11, 2021 at 5:00 pm
He and his colleagues have developed a self-learning work-aid robot. Controlled via eye detection, voice control, remote control, VR glasses and sensors on clothes, the machine learns on the job ...
- Why robots make great surgeons and crappy nurseson April 2, 2021 at 4:51 pm
Surgery is a specific skill and, for the most part, robots excel at automating tasks that require more precision than creativity. And that’s exactly why robot surgeons are commonplace ...
- Robotic fish learns to match its swimming speed to the currenton March 23, 2021 at 11:15 am
Fish have a sensory system known as the lateral line, which allows them to detect movements, vibrations and pressure gradients in the water. Scientists have now given a robotic fish its own version of ...
- Underwater swimming robot responds with feedback from soft ‘lateral line’on March 18, 2021 at 5:32 am
they tested how the air pressure controller took the reading from the sensor to measure the swimming performance of the robot – an information loop that was feeding a self-learning algorithm ...
via Google News and Bing News