HSE AI Research Centre Simplifies Particle Physics Experiments
Scientists at the HSE AI Research Centre have developed a novel approach to determining robustness in deep learning models. Their method works eight times faster than an exhaustive model search and significantly reduces the need for manual verification. It can be applied to particle physics problems using neural networks of various architectures. The study has been published in IEEE Access.
Machine learning (ML) and artificial intelligence (AI) are increasingly used in particle physics to make the analysis of experimental data easier and faster. Neural networks, for example, help process instrument signals and reconstruct missing information about particle properties. Since such predictions influence subsequent analysis, it is essential to understand how robust they are. However, in practice, model accuracy is often the only metric evaluated, and little attention is paid to how much the results may vary across different training instances. This issue is particularly pronounced for deep neural networks: their behaviour is hard to interpret, and repeated training can produce noticeably different outcomes. As a result, despite their potential advantages, many physicists remain wary of using neural networks.
Scientists at the HSE AI Centre have proposed a novel solution. They developed a method that automatically compares dozens of neural network variants and identifies the most reliable and stable ones. The idea is as follows: if a model is trained repeatedly on slightly modified data with different initial weights, the distribution of errors reveals how robust the model is to small changes in conditions. A robust model will produce nearly identical results across these tests.
The researchers tested their method on a task in which, based on an image formed by the cells of an electromagnetic calorimeter, one must determine the energy of a particle and the point at which it struck the detector. An electromagnetic calorimeter is a device made up of many cells that measure the amount of energy deposited in each cell when a particle passes through.
Fedor Ratnikov
'For the analysis, we generated half a million virtual signals simulating the detector’s operation and repeatedly fed them into different models, each time changing the training and test samples. We then used this method to identify the most reliable models and examine their properties. In doing so, we determined the minimum amount of training data required for a model to become robust—that is, to perform consistently across different training runs,' comments Fedor Ratnikov, Leading Research Fellow at the Laboratory of Methods for Big Data Analysis of the HSE AI and Digital Science Institute.
A key element of the approach is a special selection algorithm. For each model variant, the researchers collected a set of errors accumulated over dozens of independent runs and used this distribution to estimate how predictably the model behaves. This makes it possible to automatically filter out models that performed well only by chance and to identify those that remain stable under any reasonable changes in conditions.
Alexey Boldyrev
'We repeatedly trained all the models on half a million calorimeter simulation events, each time splitting the data into new training and test sets and initialising the weights randomly. This allowed us not only to measure how often each model made mistakes but also to track how its learning behaviour changed from one run to the next,’ comments Alexey Boldyrev, Research Fellow at the Laboratory of Methods for Big Data Analysis of the AI and Digital Science Institute.
The study also showed that models supplied not only with raw signals but also with simple, pre-known physical values require less data and reach stable results more quickly. The authors estimated the minimum amount of data needed for such models to maintain consistent performance across runs and identified two architectures that were reliably accurate and robust.
Andrey Shevelev
'The new method allows for much faster selection of robust AI models for certain particle physics problems—achieving results eight times more quickly than the traditional exhaustive search of all model variants,' comments Andrey Shevelev, Research Assistant at the Laboratory of Methods for Big Data Analysis of the AI and Digital Science Institute.
The researchers emphasise that the algorithm is fully automated and does not require manual tuning. As a result, it can serve as the foundation for self-learning systems that operate robustly, regardless of fluctuations in the training data or inherent model limitations.
See also:
HSE MIEM and MTS Launch Workshop on Innovative Solutions in Communication Networks
The HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM) and MTS are launching a joint workshop in which students will work at the intersection of communications network engineering, data analysis, and digital technologies. The project is designed as a practice-oriented learning format, enabling students to tackle real industry challenges alongside company engineers and MIEM specialists. Registration to participate in the workshop is open until April 15, 2026.
HSE Scientists Uncover Mechanism Behind Placental Lipid Metabolism Disorders in Preeclampsia
Scientists at HSE University have discovered that in preeclampsia—one of the most severe complications of pregnancy—the placenta remodels its lipid metabolism, reducing its own cholesterol synthesis while increasing cholesterol transfer to the foetus. This compensatory mechanism helps sustain foetal nutrition but accelerates placental deterioration and may lead to preterm birth. The study findings have been published in Frontiers in Molecular Biosciences.
HSE Experts Reveal Low Accuracy of Technology Forecasts in Transportation
HSE researchers evaluated the accuracy of technology forecasts in the transportation sector over the past 50 years and found that the average accuracy rate does not exceed 25%, with the lowest accuracy observed in aviation and rail transport. According to the scientists, this is due to limitations of the forecasting method and the inherent complexities of the sector. The study findings have been published in Technological Forecasting and Social Change.
Wearable Device Data and Saliva Biomarkers Help Assess Stress Resilience
A team of scientists, including researchers from HSE University, has proposed a method for assessing stress resilience using physiological markers derived from wearable devices and saliva samples. The participants who adapted better to stress showed higher heart rate variability, higher zinc concentrations in saliva, and lower potassium levels. The findings were published in the Journal of Molecular Neuroscience.
HSE Unveils Anthropomorphic Courier Robot
From April 1 to 3, 2026, the Fourth Robotics Festival took place, with the HSE Faculty of Computer Science acting as the main organiser. The event featured the presentation of the anthropomorphic courier robot Arkus. The humanoid was introduced by the Institute for Robotic Systems, established jointly by HSE University and the EFKO Group of Companies.
When Circumstances Are Stronger Than Habits: How Financial Stress Affects Smoking Cessation
HSE researchers have found that the likelihood of quitting smoking rises with increasing financial struggles. While low levels of financial difficulties do not affect smoking behaviour, moderate financial stress can increase the probability of quitting by 13% to 21%. Responses to high financial stress differ by gender: men are almost 1.5 times more likely to give up cigarettes than under normal conditions, whereas no significant effect is observed on women’s decisions to quit smoking. These conclusions are based on data from the Russia Longitudinal Monitoring Survey (RLMS-HSE) for 2000–2023 and have been published in Monitoring of Public Opinion: Economic and Social Changes.
HSE Researchers Propose New Method of Verbal Fluency Analysis for Early Detection of Cognitive Impairment
Researchers from the HSE Center for Language and Brain and the Mental Health Research Centre have proposed a new method of linguistic analysis that enables the distinction between normal and pathological ageing. Using this approach, they showed that patterns in patients’ word choices during verbal fluency tests allow clinicians to more accurately differentiate clinically significant impairments from subjective memory complaints. Incorporating this type of analysis into clinical practice could improve the accuracy of early dementia diagnosis. The results have been published in Applied Neuropsychology: Adult.
How the Brain Processes a Word: HSE Researchers Compare Reading Routes in Adults and Children
Researchers from the HSE Center for Language and Brain used magnetoencephalography to study how the brains of adults and children respond to words during reading. They showed that in children the brain takes longer to process words that are frequently used in everyday speech, while rare words and pseudowords are processed in the same way—slowly and in parts. With age, the system is reorganised: high-frequency words shift to a fast route, whereas new letter combinations are still analysed slowly. The study was published in the journal Psychophysiology.
How Neural Networks Detect and Interpret Wordplay: New Insights from HSE Researchers
An international team including researchers from the HSE Faculty of Computer Science has presented KoWit-24, an annotated dataset of 2,700 Russian-language Kommersant news headlines containing wordplay. The dataset enables an assessment of how artificial intelligence detects and interprets wordplay. Experiments with five large language models show that even advanced systems still make mistakes, and that interpreting wordplay is more challenging for them than detecting it. The results were presented at the RANLP conference; the paper is available on Arxiv.org, and the dataset and the code for reproducing the experiments are available on GitHub.
HSE Economists Find That Auction Prices Depend on Artist’s Life Story
Researchers from the Centre for Big Data in Economics and Finance at the HSE Faculty of Economic Sciences have found that facts from an artist’s life are statistically significant in pricing a painting, alongside such traditional characteristics as the material, the size of the canvas, or the presence of the artist’s signature. This conclusion is based on an analysis of prices for 15,000 works by 158 artists sold since 1999 by the major auction houses Sotheby’s and Christie’s. The article has been published in the journal Empirical Studies of the Arts.