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
Robot picker solution employs machine learning
on June 19, 2018 at 2:15 am
Integrated with its PickCenter Rovolution module, the new intelligent, self-learning and flexible Rovolution robots add a new element of the FlashPick solution. The modular concept of FlashPick allows for upgrades or replacements whenever needed. […]
How AI plays a key role in logistic Management
on June 14, 2018 at 8:07 pm
This process of self-learning by machines is also known as machine learning. How AI making the Warehouses More Advanced Many different eCommerce companies have already started utilising the robots to automate the process of product sorting and packaging. […]
This AI software knows what you're going to do next
on June 14, 2018 at 12:54 pm
For decades now we've been waiting for the robot butler or smart home that knows what we need ... of Bonn say they've taken an important first step in creating a self-learning computer program that can anticipate our next actions -- in the kitchen, at ... […]
Skoda Auto uses fully autonomous transport robot at Vrchlabi plant
on June 12, 2018 at 1:12 am
self-learning transport robot at the Vrchlabi component plant. This robot is able to recognise obstacles along its journey through the plant and to incorporate other information from its surroundings when planning its route, the company said in a release. […]
Škoda Auto uses fully autonomous transport robot at Vrchlabí plant
on June 11, 2018 at 11:31 pm
Škoda Auto is advancing the digitalisation of its production process. As of now, the Czech car manufacturer is using a fully autonomous, self-learning transport robot at the Vrchlabí component plant. This robot is able to recognise obstacles along its ... […]
With Robots in Control, Chemical Makers Fight for Their Formulas
on June 11, 2018 at 9:00 pm
The latest offerings -- part of a broader move to digitalization known as Industry 4.0-- embodies self-learning robots designed for the autonomous plants of the future. Although Europe this month tightened the rules on data protection for individuals ... […]
Humans will learn to confide in their robot friends, says AI expert
on June 8, 2018 at 3:29 am
He built his first self-learning computer program at 15 and now his Swiss lab ... Professor Schmidhuber, 55, said people would feel confident confessing to a human-sounding robot because they think it would keep their secrets. He said: “Today, there ... […]
KIT to showcase self-learning humanoid robot at CEBIT
on May 28, 2018 at 5:00 am
At their joint booth at CEBIT in Hanover (Hall 27, booth G52) from June 12-15, Karlsruhe Institute of Technology (KIT) and FZI Research Center for Information Technology at the Karlsruhe Institute of Technology will showcase an assistant robot for the ... […]
Self-Learning Robots Could Soon Be Used To Inspect Nuclear Sites
on May 7, 2018 at 10:51 pm
There are obvious dangers to sending humans to inspect nuclear sites, especially if those nuclear sites might be leaking, have leaked, or are hazardous. Granted there are safety measures in place to try and protect humans who do these jobs, but it is clear ... […]
via Google News and Bing News