Goto

Collaborating Authors

 amrc


Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency

Neural Information Processing Systems

Time series forecasting plays a pivotal role in critical domains such as energy management and financial markets. Although deep learning-based approaches (e.g., MLP, RNN, Transformer) have achieved remarkable progress, the prevailing long-sequence information gain hypothesis exhibits inherent limitations. Through systematic experimentation, this study reveals a counterintuitive phenomenon: appropriately truncating historical data can paradoxically enhance prediction accuracy, indicating that existing models learn substantial redundant features (e.g., noise or irrelevant fluctuations) during training, thereby compromising effective signal extraction. Building upon information bottleneck theory, we propose an innovative solution termed Adaptive Masking Loss with Representation Consistency (AMRC), which features two core components: 1) Dynamic masking loss, which adaptively identified highly discriminative temporal segments to guide gradient descent during model training; 2) Representation consistency constraint, which stabilized the mapping relationships among inputs, labels, and predictions. Experimental results demonstrate that AMRC effectively suppresses redundant feature learning while significantly improving model performance. This work not only challenges conventional assumptions in temporal modeling but also provides novel theoretical insights and methodological breakthroughs for developing efficient and robust forecasting models. We have made our code available at \url{https://github.com/MazelTovy/AMRC}.


Conversational AI โ€“ Could The Future Be About Less Data, Not Big Data?

#artificialintelligence

AI and big data are perfect companions, right? It's indisputable that access to huge volumes of data allows AI assistants to deliver better, faster, more-accurate responses. But there are downsides too. For example, is this reliance on huge amounts of data sustainable or ethical? And if you need 1,000,000 examples to create an application, do time and money become too big a barrier for many developments?


SAS partnership with AMRC will drive manufacturing innovation HG Insights

#artificialintelligence

Tech Intelligence Bulletin (HG Insights) โ€“ SAS has become a tier one partner with the University of Sheffield Advanced Manufacturing Research Centre (AMRC), a network of world-leading research and innovation centers working with manufacturing companies of all sizes from around the globe. The parties will work together to identify specific pain areas in the manufacturing industry and seek to solve those business problems using SAS software, and methods and principles of advanced analytics. The AMRC aims to transform industrial and economic performance by making step changes in productivity, increasing competitiveness, developing new products and processes and training new talent and skills. It is made up of more than 125 member organizations, ranging from global giants to SMEs offering specialist equipment and services. Like other industries, manufacturing is seeing a drive towards digital transformation, thanks to more and more data being generated more quickly than ever before, greater connectivity, greater compute power and the ability to extract actionable insights from this data using analytics.


Advanced Manufacturing Research Centre

#artificialintelligence

The AMRC is helping lead a revolution in the UK. Inside its glass-walled, state-of-the-art Factory 2050 facility in Sheffield, the centre develops digital-driven solutions that employ AI, Internet of Things (IoT), robotic and other emerging technologies, all with the aim to solve real-world manufacturing problems. Once considered futuristic, these solutions are ready for full scale deployment today, helping UK manufacturers increase their performance while fueling the Fourth Industrial Revolution. "The whole ethos behind the AMRC is to maintain UK competitiveness in global manufacturing," explains Tom Hodgson, Theme Lead, Inspection and AI, AMRC. "We take ideas that come out of the universities, where they've been developed to a prototype level. Then, with our partner companies, we conduct research projects to transition those technologies into production environments."


High Value Manufacturing Catapult

#artificialintelligence

The future of AI manufacturing is now as the Advanced Manufacturing Research Centre (AMRC) โ€“ part of High Value Manufacturing Catapult โ€“ introduces cutting edge IBM AI hardware to Factory 2050. "This is the first industry-focused AI system of its kind in the UK. It's the result of the very close relationship with IBM we have developed over recent years, enabling the AMRC to open up another dimension of Industry 4.0 for our partners, and the wider supply chain." The hardware enables AMRC researcher engineers to shred the time it takes to develop an algorithmic model from weeks down to a few hours. As backbone to this capacity and some of the world's largest supercomputers, the IBM Power9 AC922 server is a game changer.


How AI and Machine Learning Are Improving Manufacturing Productivity - AI Trends

#artificialintelligence

Engineers at the Advanced Manufacturing Research Centre's Factory 2050 in Sheffield, UK are using Artificial Intelligence (AI) to learn what machine utilization looks like on the workshop floor. The aim is to create a demonstrator to show just how accessible Industry 4.0 technologies are, and how they can potentially revolutionize shop-floor productivity. The demonstrator will be the first created under an emerging AI strategy being produced at Factory 2050, which seeks to harness the innovative work being done with AI and machine learning techniques across the Advanced Manufacturing Research Centre (AMRC) and provide real use-cases for these techniques in industrial environments. "Using edge computing devices retrofitted to CNC machines, we have collected power consumption data during the production of automotive suspension components," said Rikki Coles, AI Project Engineer for the AMRC's Integrated Manufacturing Group at Factory 2050. "It isn't a complicated parameter to measure on a CNC machine, but using AI and machine learning, we can actually do a lot with such simple data."


Inside the shape-shifting VR factory of manufacturing's future

New Scientist

Not quite yet: Factory 2050 in Sheffield, UK, isn't building anything you can buy. Instead, the brains behind the project are rethinking the manufacturing process itself, aiming to change how we make everything from airplanes to nuclear power plants. Inside the factory, things are looking a little unfinished. It opened in January, and the team from the University of Sheffield's Advanced Manufacturing Research Centre (AMRC) are still moving in. The place is sparkling clean, and smells like a newly furnished IKEA, but it's gearing up to change the way whole industries work by applying virtual reality, robotics and bitcoin's blockchain.