(Press-News.org) Applying machine learning to find the properties of atomic pieces of geometry shows how AI has the power to accelerate discoveries in maths.
Mathematicians from Imperial College London and the University of Nottingham have, for the first time, used machine learning to expand and accelerate work identifying ‘atomic shapes’ that form the basic pieces of geometry in higher dimensions. Their findings have been published in Nature Communications.
The way they used artificial intelligence, in the form of machine learning, could transform how maths is done, say the authors. Dr Alexander Kasprzyk from the University of Nottingham said: “For mathematicians, the key step is working out what the pattern is in a given problem. This can be very difficult, and some mathematical theories can take years to discover.”
Professor Tom Coates, from the Department of Mathematics at Imperial, added: “We have shown that machine learning can help uncover patterns within mathematical data, giving us both new insights and hints of how they can be proved.”
PhD student Sara Veneziale, from the Department of Mathematics at Imperial, said: “This could be very broadly applicable, such that it could rapidly accelerate the pace at which maths discoveries are made. It’s like when computers were first used in maths research, or even calculators: it’s a step-change in the way we do maths.”
Defining shapes
Mathematicians describe shapes using equations, and by analysing these equations can break the shape down into fundamental pieces. These are the building blocks of shapes, the equivalent of atoms, and are called Fano varieties.
The Imperial and Nottingham team began building a ‘periodic table’ of these Fano varieties several years ago, but finding ways of classifying them into groups with common properties has been challenging. Now, they have used machine learning to reveal unexpected patterns in the Fano varieties.
One aspect of a Fano variety is its quantum period – a sequence of numbers that acts like a barcode or fingerprint. It has been suggested that the quantum period defines the dimension of the Fano variety, but there has been no theoretical proposal for how this works, so no way to test it on the huge set of known Fano varieties.
Machine learning, however, is built to find patterns in large datasets. By training a machine learning model with some example data, the team were able to show the resulting model could predict the dimensions of Fano varieties from quantum periods with 99% accuracy.
Coding the real world
The AI model doesn’t conclusively show the team have discovered a new statement, so they then used more traditional mathematical methods to prove that the quantum period defines the dimension – using the AI model to guide them.
As well as using machine learning to discover new maths, the team say that the datasets used in maths could help refine machine learning models. Most models are trained on data taken from real life, such as health or transport data, which are inherently ‘noisy’ – they contain a lot of randomness that to some degree mask the real information.
Mathematical data is ‘pure’ – noise free – and contains patterns and structures that underly the data, waiting to be uncovered. This data can therefore be used as testing grounds for machine learning models, improving their ability to find new patterns.
END
Machine learning used to probe the building blocks of shapes
2023-10-04
ELSE PRESS RELEASES FROM THIS DATE:
Invertebrate biodiversity is improving in England’s rivers, long-term trends show
2023-10-04
Rivers across England have seen a significant improvement in river invertebrate biodiversity since 1989, shows a study led by UK Centre for Ecology & Hydrology (UKCEH) researchers.
The study, which involved one of the largest and most wide-ranging analyses of long-term monitoring data in the world – spanning over 30 years, found improvements in invertebrate biodiversity across all regions and river types in England.
This improvement is all the more surprising given English rivers are amongst the most highly exposed to wastewater and other pressures in Europe. The recent State of Nature report shows that the overall abundance of species in Great ...
LSU Health New Orleans’ Porche awarded top honor by National League for Nursing
2023-10-04
New Orleans – The National League for Nursing (NLN) presented Demetrius Porche, DNS, PhD, ANEF, FACHE, FAANP, FAAN, Professor and Dean of LSU Health New Orleans School of Nursing, with its Mary Adelaide Nutting Award for Outstanding Teaching or Leadership in Nursing Education during the 2023 NLN Education Summit. The Annual NLN Awards recognize and honor individuals of stature and distinction for their outstanding contributions to nursing education and the broader space of health care.
The NLN Mary Adelaide ...
Translational Plant Sciences Center sows seeds for new research
2023-10-04
The Translational Plant Sciences Center has awarded funding to four new research projects to help them grow and cultivate external funding.
The center provided the projects up to $10,000 a year for up to two years to support the development of innovative research leading to extramural support through the Translational Plant Sciences Center (TPSC) Seed Grant program.
“This program aims to provide faculty with funds to explore new research by establishing teams composed of labs and partners both inside and outside of TPSC and Virginia Tech ...
Cornell fills data gap for volcanic ash effects on Earth systems
2023-10-04
ITHACA, N.Y. -- Volcanic ash is no ordinary dust: It gets injected into the atmosphere, climbs to the stratosphere, impacts climate, powders roadways and clogs jet engines.
To bridge the knowledge gap between volcanologists and atmospheric scientists working on climate change and observing global systems, Cornell researchers have characterized volcanic ash samples from many explosive eruptions of a broad compositional range. The work is helping scientists uncover how this tiny material – measured in microns and nanometers – plays a big role in the atmosphere.
Volcanic ash is formed from minerals trapped in ...
Coaching program created at CU Anschutz reduces burnout in medical residents
2023-10-04
AURORA, Colo. (Oct. 4, 2023) – A pilot program that successfully reduced burnout among female medical residents has shown even greater results on a national level, according to researchers at the University of Colorado Anschutz Medical Campus.
The study was published today in the journal JAMA Network Open.
“We did a pilot program in 2021to see if it would work and it did,” said study co-author Tyra Fainstad, MD, associate professor at the University of Colorado School of Medicine. “Then we expanded it to 26 graduate medical institutions in 19 states. There were 1,017 participants. We saw significant improvement in every wellbeing outcome we assessed including all ...
MD Anderson Research Highlights for October 4, 2023
2023-10-04
HOUSTON ― The University of Texas MD Anderson Cancer Center’s Research Highlights showcases the latest breakthroughs in cancer care, research and prevention. These advances are made possible through seamless collaboration between MD Anderson’s world-leading clinicians and scientists, bringing discoveries from the lab to the clinic and back.
Recent developments at MD Anderson include a computer game that helps breast cancer survivors improve symptoms of peripheral neuropathy, a publicly available single-cell atlas of CD19 chimeric antigen receptor (CAR) T cells, new targets for TP53-mutant acute myeloid leukemia (AML), a preclinical target ...
Cancer immunotherapy candidate provokes powerful dual response in cancer and immune cells
2023-10-04
Cancer immunotherapy drugs called PD-1 inhibitors are widely used to stimulate the immune system to fight cancer, but many patients either don’t respond or develop resistance to them. A new small-molecule drug candidate being tested in an early-stage clinical trial aims to improve patient responses to immunotherapy.
Now scientists have shown, in a study published today in Nature, that the small molecule works through two different mechanisms to slow tumor growth and increase survival in lab animals.
Researchers from the Tumor ...
Research shows strong link between ADHD and car crashes in older adult drivers
2023-10-04
In a study on the prevalence of attention-deficit/hyperactivity disorder (ADHD) and its association with crash risk among older adult drivers, researchers at Columbia University Mailman School of Public Health found that older adult drivers with ADHD are at a significantly elevated crash risk compared with their counterparts without ADHD. Outcomes included hard- braking events, and self-reported traffic ticket events, and vehicular crashes. Until now research on ADHD and driving safety was largely limited to ...
Pediatric RSV-associated hospitalizations before and during the pandemic
2023-10-04
About The Study: This study found that the burden of respiratory syncytial virus (RSV)-associated hospitalizations in Canadian pediatric hospitals was substantial, particularly among infants less than six months of age, and RSV hospitalizations increased in 2021-2022 compared with the pre-pandemic period, while severity of illness remained similar. These findings suggest that RSV preventive strategies for infants less than six months of age would be associated with decreased RSV disease burden in children.
Authors: Jesse Papenburg, ...
Prevalence, trends in diagnosed ADHD among children and adolescents
2023-10-04
About The Study: Based on U.S. national representative data, the estimated attention-deficit hyperactivity disorder (ADHD) prevalence was 10.08% to 10.47% among children and adolescents ages 4 to 17 from 2017 to 2022, which was similar to the prevalence from the National Health Interview Survey in 2015 to 2016 (10.20%). No significant annual change in the prevalence of ADHD was found from 2017 to 2022. Notably, the estimated prevalence of ADHD among individuals in the U.S. in this study was higher than worldwide estimates (5.3%) in earlier years (1978-2005).
Authors: Wenhan Yang, M.D., Ph.D., of Guangdong ...