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
- Our robot partners: Inside a research lab exploring the future of human-machine collaborationon May 20, 2022 at 12:14 pm
The biggest potential for robots and automation isn’t taking jobs from humans, but instead making those jobs better by allowing people to do what they do best. That’s… Read More ...
- Researchers design 'socially aware' robots that can anticipate and safely avoid people on the moveon May 18, 2022 at 8:14 am
A team of researchers led by University of Toronto Professor Tim Barfoot is using a new strategy that allows robots to avoid colliding with people by predicting the future locations of dynamic ...
- Autonomous Mobile Robot Marketon May 17, 2022 at 9:10 am
Autonomous mobile robot market to reach $12.42 Bn in 2030, Self driving forklifts to rise at 19% CAGR; Warehouse fleet management to rake at 20% CAGR.
- Your next Uber Eats order could arrive by self-driving car or robot. What now for workers?on May 17, 2022 at 6:53 am
Uber has launched two autonomous delivery pilots in Los Angeles. The announcement has raised concerns regarding workers rights.
- A Guy Spotted A Delivery Robot “Lost In The Woods,” But We'd Like To Think It Was Just Trying To *Find* Itselfon May 16, 2022 at 12:46 pm
Also enjoying the scenery was a white self-driving delivery robot, its lights flashing and its antenna in ... And while the robot is, well, not living, that doesn’t mean we can’t learn from its ...
- Sad Delivery Robot Gets Lost In The Woodson May 16, 2022 at 7:36 am
British history professor Matthew McCormack made a rather strange discovery during his morning bike ride: a delivery robot seemingly lost in the woods.
- Never scoop poop again with the sleek, brilliantly designed Litter-Robot 4on May 13, 2022 at 9:04 am
Designed with community feedback in mind, the latest Litter-Robot is all about improving on all the pain points from previous models – notably it’s less noisy, bulky and smelly. Ahead, everything to ...
- The Delivery Robots Market size is expected to reach USD 957 million by 2026 from USD 212 million in 2021on May 13, 2022 at 8:05 am
"Delivery Robots Market"Delivery robots market size is projected to grow from USD 212 million in 2021 to USD 957 million by 2026, at a CAGR of 35.1% from ...
- Who Is More Able to Connect with Robots?on May 12, 2022 at 7:10 am
In their study, humans were generally categorized into displaying one of four types of attachment in interpersonal relationships: secure, as demonstrated by a positive view of the self ... robot as a ...
- Here's My Honest Review of the Self-Cleaning Litter-Robot 4on May 11, 2022 at 2:07 pm
The new Litter-Robot 4 features improvements and innovative features for your cat's health. Here's our review after testing the latest self-cleaning litter box.
via Google News and Bing News