
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
[google_news title=”” keyword=”self-learning robots” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
- Roomba 694 Review: The Best Roomba For Daily Maintenanceon February 3, 2023 at 12:58 pm
Though the Roomba 694 isn’t the smartest or most advanced option from iRobot, it is the most affordable, and it’s a great way to stay on top of routine vacuuming. I now rely on it to keep my floors ...
- The Best Roombas: Here Are The Top 5 Modelson February 2, 2023 at 10:34 am
Some models can map and “learn” your house, while others can target specific messes and avoid obstacles. (I tested the Roomba 694 over three weeks to see how well Roomba’s most affordable model ...
- Flexiv Showcases Its Latest Adaptive Robotic Solutions at ATX West 2023on February 2, 2023 at 7:39 am
SAN JOSE, Calif., February 02, 2023--Flexiv, a world leader in general-purpose robotics solutions, is proud to announce that it will be attending ATX West, the largest annual event for automation and ...
- How robots and our school’s buddy program bring computer science to lifeon February 1, 2023 at 2:00 am
Coding and robots are both natural tools for encouraging collaboration in the classroom. At Sewickley Academy, we have taken that collaboration to the next level by having Grade 5 students step ...
- Imitation and Social Learning in Robots, Humans and Animalson January 30, 2023 at 2:15 am
Imitation and Social Learning in Robots, Humans, and Animals advances our understanding ... Mirrors and matchings: imitation from the perspective of mirror-self-recognition and the parietal region's ...
- These robots might build your houseon January 30, 2023 at 2:00 am
The construction industry is in a crisis, and more companies are turning to robots to automate tasks on the job site.
- Sensory finger: Startup teaches robots the feeling of a touchon January 29, 2023 at 6:45 am
A new startup is claiming that the next generation of robotics will feature sensory skins, fabricated muscles and artificial neurons that will allow them to feel.
- Hate self-checkout? Get ready for a change you never expectedon January 28, 2023 at 4:00 am
The company's CEO, Jason Souloglou, told me: "Trials are expected to be complete by Q1 and deployed within US retailers in Q2 this year." Which leaves you only one more problem with self-checkout: ...
- If we have self-healing bio robots in 2053, it started here with mouse muscle cyborgson January 23, 2023 at 5:25 pm
Updated What do you get when you stretch mouse muscle tissue over a polymer skeleton and attach electronics capable of converting radio-frequency energy into light? Perhaps a bit of shock when the ...
via Google News and Bing News