Researchers from the University of Copenhagen have become the first in the world to mathematically prove that, beyond simple problems, it is impossible to develop algorithms for AI that will always be stable.
ChatGPT and similar machine learning-based technologies are on the rise. However, even the most advanced algorithms face limitations. Researchers from the University of Copenhagen have made a groundbreaking discovery, mathematically demonstrating that, beyond basic problems, it’s impossible to develop AI algorithms that are always stable. This research could pave the way for improved testing protocols for algorithms, highlighting the inherent differences between machine processing and human intelligence.
The scientific article describing the result has been approved for publication at one of the leading international conferences on theoretical computer science.
Machines interpret medical scanning images more accurately than doctors, translate foreign languages, and may soon be able to drive cars more safely than humans. However, even the best algorithms do have weaknesses. A research team at the Department of Computer Science, University of Copenhagen, tries to reveal them.
Take an automated vehicle reading a road sign as an example. If someone has placed a sticker on the sign, this will not distract a human driver. But a machine may easily be put off because the sign is now different from the ones it was trained on.
“We would like algorithms to be stable in the sense, that if the input is changed slightly the output will remain almost the same. Real life involves all kinds of noise which humans are used to ignore, while machines can get confused,” says Professor Amir Yehudayoff, heading the group.
A language for discussing weaknesses
As the first in the world, the group together with researchers from other countries has proven mathematically that apart from simple problems it is not possible to create algorithms for Machine Learning that will always be stable. The scientific article describing the result was approved for publication at one of the leading international conferences on theoretical computer science, Foundations of Computer Science (FOCS).
“I would like to note that we have not worked directly on automated car applications. Still, this seems like a problem too complex for algorithms to always be stable,” says Amir Yehudayoff, adding that this does not necessarily imply major consequences in relation to the development of automated cars:
“If the algorithm only errs under a few very rare circumstances this may well be acceptable. But if it does so under a large collection of circumstances, it is bad news.”
The scientific article cannot be applied by the industry to identify bugs in its algorithms. This wasn’t the intention, the professor explains:
“We are developing a language for discussing the weaknesses in Machine Learning algorithms. This may lead to the development of guidelines that describe how algorithms should be tested. And in the long run, this may again lead to the development of better and more stable algorithms.”
From intuition to mathematics
A possible application could be for testing algorithms for the protection of digital privacy.
”Some companies might claim to have developed an absolutely secure solution for privacy protection. Firstly, our methodology might help to establish that the solution cannot be absolutely secure. Secondly, it will be able to pinpoint points of weakness,” says Amir Yehudayoff.
First and foremost, though, the scientific article contributes to theory. Especially the mathematical content is groundbreaking, he adds: ”We understand intuitively, that a stable algorithm should work almost as well as before when exposed to a small amount of input noise. Just like the road sign with a sticker on it. But as theoretical computer scientists, we need a firm definition. We must be able to describe the problem in the language of mathematics. Exactly how much noise must the algorithm be able to withstand, and how close to the original output should the output be if we are to accept the algorithm to be stable? This is what we have suggested an answer to.”
Important to keep limitations in mind
The scientific article has received large interest from colleagues in the theoretical computer science world, but not from the tech industry. Not yet at least.
”You should always expect some delay between a new theoretical development and interest from people working in applications,” says Amir Yehudayoff while adding smilingly: ”And some theoretical developments will remain unnoticed forever.”
However, he does not see that happening in this case: ”Machine Learning continues to progress rapidly, and it is important to remember that even solutions which are very successful in the real world still do have limitations. The machines may sometimes seem to be able to think but after all, they do not possess human intelligence. This is important to keep in mind.”
Reference: “Replicability and Stability in Learning” by Zachary Chase, Shay Moran and Amir Yehudayoff, 2023, Foundations of Computer Science (FOCS) conference.
DOI: 10.48550/arXiv.2304.03757
News
The Global Nanomedicine Market: Key Players and Emerging Technologies in Healthcare
This article provides an overview of the global nanomedicine market, highlighting key players, emerging technologies, and the challenges and opportunities that influence its growth and commercialization in the healthcare sector. Nanomedicines are nanotechnology-based drug products [...]
Scientists Have Discovered Toxic “Forever Chemicals” in Bottled Water
Scientists have found toxic PFAS in drinking water samples from around the world, with higher levels in tap water from China compared to the UK. Boiling water or using a filtration jug can reduce [...]
Urban Microbes Are Eating Disinfectants – Are We Fueling a New Health Threat?
New research reveals that microbes in urban environments are evolving to withstand the very cleaning agents designed to eliminate them. The study also uncovers new strains in Hong Kong, previously only found in the [...]
Startling Study Shows High-Potency Cannabis Alters DNA
The study shows that frequent use of high-potency cannabis alters DNA, affecting genes related to energy and immune function. These changes differ between those with and without psychosis, suggesting cannabis use could influence mental health through biological [...]
New nanotherapy targets artery inflammation in cardiovascular disease
Inflammation of the arteries is a primary precursor and driver of cardiovascular disease—the No. 1 killer of people in the United States. This inflammation is associated with the buildup of dangerous plaque inside the [...]
Revolutionary Nanoparticle Therapy for Prostate Cancer
A groundbreaking research effort involving teams from the University of Virginia, Mount Sinai, the University of Michigan, the University of Texas, and others has displayed the clinical efficacy of an innovative therapy that utilizes nanoparticles and [...]
Antibody engineering drives innovation in drug development
Monoclonal antibodies (mAbs) are used to prevent, detect, and treat a broad spectrum of non-communicable and communicable diseases. Over the past few years, the market for mAbs has grown exponentially with an expected compound [...]
Breakthrough Study Reveals How Bladder Cancer Starts and Spreads
Researchers found that DNA mutations from antiviral enzymes and chemotherapy fuel early bladder cancer, while abnormal circular DNA in tumor cells drives resistance to therapy. These discoveries open new therapeutic avenues. A groundbreaking study led by [...]
AI and Quantum Mechanics Accelerate Drug Discovery
A recent article published in the Journal of Chemical Information and Modeling researchers at Southern Methodist University (SMU) have developed SmartCADD, an open-source virtual tool designed to speed [...]
Targeting ‘undruggable’ diseases: Researchers reveal new levels of detail in targeted protein degradation
Researchers at the University of Dundee have revealed in the greatest detail yet the workings of molecules called protein degraders which can be deployed to combat what have previously been regarded as "undruggable" diseases, [...]
Revolutionizing Virology: AI Discovers Over 160,000 New RNA Viruses
Largest discovery of new virus species sheds light on the hidden virosphere. Artificial intelligence (AI) has been used to reveal details of a diverse and fundamental branch of life living right under our feet and in every [...]
Cardiac Crisis: COVID-19 Doubles Risk of Heart Attacks, Strokes, and Death
Research indicates that COVID-19 survivors face doubled risks of severe cardiac events for years after recovery, especially if hospitalized. People with A, B, or AB blood types are particularly vulnerable, highlighting the need for personalized approaches [...]
AI steps into science limelight with Nobel wins
For long periods of its history, artificial intelligence has lurked in the hinterland of science, often unloved and unfunded—but two Nobel prizes in one week suggest its time in the sunshine has finally arrived. [...]
MIT Scientists Shed New Light on the Critical Brain Connections That Define Consciousness
A new study provides further evidence that consciousness depends on communication between the brain’s sensory and cognitive regions in the cortex. Our brains are constantly making predictions about our surroundings, enabling us to focus [...]
Common Chemicals Found in Shampoo and Plastic Could Be Quietly Disrupting Your Heart’s Rhythm
UC study of Fernald data links environmental phenols to heart toxicities Environmental phenols are present in numerous everyday consumer products, serving as preservatives in packaged foods, parabens in shampoos, and bisphenol A (BPA) in [...]
Revolutionary Brain Tech Offers New Hope for Stroke and Injury Recovery
University of Pittsburgh researchers report that deep brain stimulation (DBS) can effectively enhance motor functions in individuals with arm and hand paralysis due to brain injuries, with promising results from early human and monkey [...]