Federated Learning (FL) enables decentralized model training without sharing raw data, offering strong privacy guarantees. However, existing FL protocols struggle to defend against Byzantine participants, maintain model utility under non-independent and identically distributed (non-IID) data, and remain lightweight for edge devices. Prior work either assumes trusted hardware, uses expensive cryptographic tools, or fails to address privacy and robustness simultaneously. We propose DSFL, a Dual-Server Byzantine-Resilient Federated Learning framework that addresses these limitations using a group-based secure aggregation approach. Unlike LSFL, which assumes non-colluding semi-honest servers, DSFL removes this dependency by revealing a key vulnerability: privacy leakage through client-server collusion. DSFL introduces three key innovations: (1) a dual-server secure aggregation protocol that protects updates without encryption or key exchange, (2) a group-wise credit-based filtering mechanism to isolate Byzantine clients based on deviation scores, and (3) a dynamic reward-penalty system for enforcing fair participation. DSFL is evaluated on MNIST, CIFAR-10, and CIFAR-100 under up to 30 percent Byzantine participants in both IID and non-IID settings. It consistently outperforms existing baselines, including LSFL, homomorphic encryption methods, and differential privacy approaches. For example, DSFL achieves 97.15 percent accuracy on CIFAR-10 and 68.60 percent on CIFAR-100, while FedAvg drops to 9.39 percent under similar threats. DSFL remains lightweight, requiring only 55.9 ms runtime and 1088 KB communication per round.

As the use of artificial intelligent (AI) models becomes more prevalent in industries such as engineering and manufacturing, it is essential that these models provide transparent reasoning behind their predictions. This paper proposes the AI-Reasoner, which extracts the morphological characteristics of defects (DefChars) from images and utilises decision trees to reason with the DefChar values. Thereafter, the AI-Reasoner exports visualisations (i.e. charts) and textual explanations to provide insights into outputs made by masked-based defect detection and classification models. It also provides effective mitigation strategies to enhance data pre-processing and overall model performance. The AI-Reasoner was tested on explaining the outputs of an IE Mask R-CNN model using a set of 366 images containing defects. The results demonstrated its effectiveness in explaining the IE Mask R-CNN model's predictions. Overall, the proposed AI-Reasoner provides a solution for improving the performance of AI models in industrial applications that require defect analysis.

British universities are popular globally for producing highly competent AI experts. This is why many aspiring AI specialists enroll themselves in the MS in AI programs of British universities. However, not all British universities are created equal and provide quality AI training to students. So, to help you out today we are sharing with you the top six universities for studying Masters in Artificial Intelligence in UK. Here are some of the best universities in the UK that you can join to study AI.

A resistor that works in a similar way to nerve cells in the body could be used to build neural networks for machine learning. Many large machine learning models rely on increasing amounts of processing power to achieve their results, but this has vast energy costs and produces large amounts of heat. One proposed solution is analogue machine learning, which works like a brain by using electronic devices similar to neurons to act as the parts of the model. However, these devices have so far not been fast, small or efficient enough to provide advantages over digital machine learning. Murat Onen at the Massachusetts Institute of Technology and his colleagues have created a nanoscale resistor that transmits protons from one terminal to another.

DECODE is a 30-month research project funded by the NIHR Artificial Intelligence for Multiple Long-Term Conditions (AIM) Programme. This project is led by Loughborough University (PI: Dr Gyuchan Thomas Jun, Reader in Socio-technical System Design) jointly with Leicestershire Partnership NHS Trust (joint PI: Dr Satheesh Gangadharan, Consultant Psychiatrist). Overall, the project team consists of fifteen co-investigators with expertise in the field of intellectual disabilities, neuropsychiatry, epidemiology, health data science, machine learning, data visualisation, human factors, qualitative research and ethics from eight institutions. The co-investigators include Dr Georgina Cosma (AI and data science) and Dr Panos Balatsoukas (UX design) at Loughborough University, Dr Francesco Zaccardi (epidemiology), Dr Michelle O'Reilly (qualitative research) and Prof Kamlesh Khunti (primary care) at the University of Leicester, Ashley Akbari (data science) and Prof Simon Ellwood-Thompson (health informatics) at Swansea University, Dr Vasa Curcin (AI) at King's College London, Prof Rohit Shankar (neuropsychiatry) at the University of Plymouth, Dr Reza Kiani (intellectual disabilities) at Leicestershire Partnership NHS Trust, Dr Neil Sinclair (ethics) at the University of Nottingham, Dr Chris Knifton (nursing) at De Montfort University, and Gillian Huddleston (PPI lead). The DECODE project aims to improve the health and wellbeing of people with intellectual disabilities (also known as learning disabilities) by developing actionable insights to support a model of effective care coordination using machine learning aided analysis of multiple long-term conditions in people with intellectual disabilities.

The aim behind a new international project is to develop advanced AI programs that will allow machines to learn gradually over a lifetime and share that input with each other. Scientists are optimistic that the technology will enable machines to reuse data, adapt rapidly to new conditions and work in partnership by sharing data. The project comes under the initiative known as Shared-Experience Lifelong Learning (ShELL), a program financially supported by the Defense Advanced Research Projects Agency (DARPA) -- a U.S. government agency known for some major technological developments in recent history such as the Internet, Siri, the miniaturization of GPS and the computer mouse. It began this month and is being headed by Dr. Andrea Soltoggio of Loughborough's Computer Science department, in partnership with Dr. Soheil Kolouri at Vanderbilt University and Dr. Cong Liu at the University of Texas at Dallas, both in the United States. The idea behind this project is to gain a deep understanding of how and what an AI system learns when dealing with a new task, so that we can exploit task similarities and share information to create fast, reliable, and collaborating learning agents.

Computer scientists at Loughborough University in the U.K. have developed artificial intelligence algorithms that could revolutionize player performance analysis for football (soccer) clubs. Computer scientists at Loughborough University in the U.K. have developed artificial intelligence algorithms that could revolutionize player performance analysis for football (soccer) clubs. The researchers designed a hybrid system that accelerates and supplements human data entry with camera-based automation to meet demand for timely performance data generated from large amounts of videos. The team applied the latest computer vision and deep learning technologies to identify actions by detecting players' body poses and limbs, and trained the deep neural network to track individual players and capture data on individual performance throughout the match video. Loughborough's Baihua Li said the new technology "will allow a much greater objective interpretation of the game as it highlights the skills of players and team cooperation."

Imagine being scared to breathe the air around you. An unusual concept for us here in the UK, but it is a genuine concern for communities all over the world with air pollution killing an estimated seven million people every year. A team of Loughborough University computer scientists are hoping to help eradicate this fear with a new artificial intelligence (AI) system they have developed that can predict air pollution levels hours in advance. The technology is novel for a number of reasons, one being that it has the potential to provide new insight into the environmental factors that have significant impacts on air pollution levels. Professor Qinggang Meng and Dr. Baihua Li are leading the project which is focused on using AI to predict PM2.5--particulate matter of less than 2.5 microns (10-6 m) in diameter--that is often characterized as reduced visibility in cities and hazy-looking air when levels are high.

Loughborough University and the Willis Research Network (WRN) would like to invite you to another conference bringing together a range of perspectives on the business application of Artificial Intelligence (AI) and its role in the ongoing digital transformation of the insurance industry. The goal is to look beyond the day to day business decision-making and examine the broader challenges of employing AI, the implication for business models and to address some of the organisational and public policy challenges to effective use of these new technologies. We will have a mix of top university researchers and industry practitioners participating as both presenters and panellists to enhance our depth of knowledge around AI and the use of AI in our industry. We look forward to welcoming you to a stimulating day of open debate and insightful discussion. The conference is the first major event organised by the TECHNGI research project, hosted by Loughborough University and Willis Towers Watson and funded from the UK Government Industry Challenge Fund's Next Generation Services program.

A funded PhD position is available at the Computer Science Department, School of Science, Loughborough University, UK, on the topic of the evolution of lifelong learning in neural networks. The aim is to develop new neuroevolution algorithms for lifelong learning. The objectives are to devise machine learning systems that autonomously adapt to changing conditions such as variation of the data distribution, variation of the problem domain or parameters, with minimal human intervention. The approach will use neuroevolution, neuromodulation, and other methodologies to continuously discover and update learning strategies, implement selective plasticity, and achieve continual learning. Application areas include a variety of automation and machine learning problems, e.g.