Current techniques for deep neural network (DNN) pruning often involve intricate multi-step processes that require domain-specific expertise, making their widespread adoption challenging. To address the limitation, the Only-Train-Once (OTO) and OTOv2 are proposed to eliminate the need for additional fine-tuning steps by directly training and compressing a general DNN from scratch. Nevertheless, the static design of optimizers (in OTO) can lead to convergence issues of local optima. In this paper, we proposed the Auto-Train-Once (ATO), an innovative network pruning algorithm designed to automatically reduce the computational and storage costs of DNNs. During the model training phase, our approach not only trains the target model but also leverages a controller network as an architecture generator to guide the learning of target model weights. Furthermore, we developed a novel stochastic gradient algorithm that enhances the coordination between model training and controller network training, thereby improving pruning performance. We provide a comprehensive convergence analysis as well as extensive experiments, and the results show that our approach achieves state-of-the-art performance across various model architectures (including ResNet18, ResNet34, ResNet50, ResNet56, and MobileNetv2) on standard benchmark datasets (CIFAR-10, CIFAR-100, and ImageNet).

DALLAS, Nov. 15, 2022, SC22, Booth #2828 -- DDN, the global leader in artificial intelligence (AI) and multi-cloud data management solutions, today announced at SC22, The International Conference for High Performance Computing, Networking, Storage, and Analysis, a new Reference Architecture in collaboration with Atos. DDN also introduced enhancements to its scalable and flexible monitoring interface, DDN Insight, to streamline and simplify management and support of HPC and AI infrastructures at-scale. DDN worked in tight collaboration with Atos on this new Reference Architecture to advance DDN's goal of simplifying the adoption of advanced AI infrastructure for enterprises and research institutions. Historically, storage systems were often chosen to complement compute infrastructure as it was being deployed. This approach leads to silos of data and requires data movement to use the optimal compute platform for a certain stage of processing.

The new 19,200 square meter site brings together three areas of expertise (energy, high-performance computing (HPC) and artificial intelligence) and 1,000 Atos employees who were previously based at Grenoble and the historic site in Echirolles. With a capacity of up to 1,320 people, the new site will be able to accommodate the 250 new hires planned for 2023. With this new campus, Atos reinforces its innovation strategy as the new European R&D center will promote local excellence on a worldwide scale. Funded by the Auvergne-Rhône-Alpes Region, through the European Regional Development Fund (ERDF), and by Grenoble-Alpes Métropole, this center and its 300 employees are mainly focused on Artificial Intelligence. Atos' teams have already partnered with the MIAI@Grenoble Alpes program from the Grenoble Interdisciplinary Institute of Artificial Intelligence (3IA), which has received government support.

EuroHPC – its BullSequana will be used in five EuroHPC supercomputing centres – Sofia Tech Park at Bulgaria ("Discover"), CINECA in Italy ("Da Vinci"), IZUM in Slovenia, ("Vega") LuxProvide in Luxembourg ("MeluXina" which is also #4 in the GREEN500) and in the Minho Advanced Computing Centre in Portugal, reinforcing Atos' position as a European leader in high-performance computing. The Linkoping University's'Berzelius' supercomputer for AI will use Atos' recently announced Atos ThinkAI solution to enable its researchers speed-up processing times on their complex data, empowering them to gain insights faster, using the power of deep learning and analytics. "Topaze" at the CCRT – a new supercomputer at the French CCRT based on the BullSequana XH2000 solution from Atos, is the result of joint R&D by Atos and the CEA's Military Applications Directorate (DAM). It will soon be open to the first users, to start the'Grand Challenges' phase, for very large-scale simulations. "Noctua2" at Paderborn University – the recently announced "Noctua2" supercomputer at the University of Paderborn, based on Atos" BullSequana XH2000, will give the University the modern, highly available and flexible supercomputer infrastructure that is needed for excellent science and research. EuroHPC – its BullSequana will be used in five EuroHPC supercomputing centres – Sofia Tech Park at Bulgaria ("Discover"), CINECA in Italy ("Da Vinci"), IZUM in Slovenia, ("Vega") LuxProvide in Luxembourg ("MeluXina" which is also #4 in the GREEN500) and in the Minho Advanced Computing Centre in Portugal, reinforcing Atos' position as a European leader in high-performance computing. The Linkoping University's'Berzelius' supercomputer for AI will use Atos' recently announced Atos ThinkAI solution to enable its researchers speed-up processing times on their complex data, empowering them to gain insights faster, using the power of deep learning and analytics. "Topaze" at the CCRT – a new supercomputer at the French CCRT based on the BullSequana XH2000 solution from Atos, is the result of joint R&D by Atos and the CEA's Military Applications Directorate (DAM). It will soon be open to the first users, to start the'Grand Challenges' phase, for very large-scale simulations. "Noctua2" at Paderborn University – the recently announced "Noctua2" supercomputer at the University of Paderborn, based on Atos" BullSequana XH2000, will give the University the modern, highly available and flexible supercomputer infrastructure that is needed for excellent science and research.

Federal agencies are getting better at buying advanced technologies like artificial intelligence but still lag in deploying those tools due to security concerns, according to a Homeland Security Department procurement official. "We're doing a really good job at procuring things," Jessica Clark, an official on the Acquisition Systems Team in DHS's Office of the Chief Procurement Officer, said Tuesday during the Professional Services Council's annual Tech Trends conference. "But getting it up and running safely is always going to be an issue for our program managers." Clark said DHS takes a different procurement strategy when looking at new and innovative technologies, preferring a phased approach where a relatively large pool of vendors is whittled down over the course of multiple prototypes and demonstrations, with each subsequent phase using larger datasets that are more and more relevant to the program. She cited the department's work integrating AI into the Contractor Performance Assessment Reporting System, or CPARS, which contracting officers use to gauge a vendor's past performance on government contracts. For the CPARS AI effort, DHS started with nine vendors, which was then down-selected to six and then four.

National Supercomputer Centre at Linköping University has installed Berzelius, Sweden's fastest supercomputer for artificial intelligence and machine learning. The above had been made possible with a donation of EUR 29.5 million from the Knut and Alice Wallenberg Foundation. According to Jan-Ingvar Jönsson, vice-chancellor of Linköping University, It's gratifying and a big challenge at the same time that Linköping University has taken a national responsibility to connect all initiatives within high-performance computing and data processing. Berzelius is a powerful addition to the vital research carried out in such fields. Berzelius owes its name to renowned scientist Jacob Berzelius from Östergötland.

NVIDIA today announced that the Italian inter-university consortium CINECA -- one of the world's most important supercomputing centers -- will use the company's accelerated computing platform to build the world's fastest AI supercomputer. The new "Leonardo" system, built with Atos, is expected to deliver 10 exaflops of FP16 AI performance to enable advanced AI and HPC converged application use cases. Featuring nearly 14,000 NVIDIA Ampere architecture-based GPUs and NVIDIA Mellanox HDR 200 Gb/s InfiniBand networking, Leonardo will propel Italy as the global leader in AI and high performance computing research and innovation. Leonardo is procured by EuroHPC, a collaboration between national governments and the European Union to develop a world-class supercomputing ecosystem and exascale supercomputing in Europe, and funded by the European Commission through the Italian Ministry of University and Research. "The EuroHPC technology roadmap for exascale in Europe is opening doors for rapid growth and innovation in HPC and AI," said Marc Hamilton, vice president of solutions architecture and engineering at NVIDIA.

With telcos and enterprises alike fast tracking their digitalisation initiatives across the region, the Middle East finds itself on the cutting edge when it comes to digital innovation. In the Gulf Cooperation Council (GCC), the launch of 5G will bring a plethora of opportunities for enterprises to redefine the way they do business and deliver a diverse portfolio of digital services and products to an increasingly demanding client base. Similarly, across the greater Middle East and Africa region, the proliferation of 4G and LTE networks is kick starting a digital revolution that will fundamentally change the way people live their lives – opening up a veritable smorgasbord of digital opportunities, from remote working and e-learning initiatives, to mobile financial applications and e-health solutions. As telcos continue to evolve their product offering way beyond the mere provision of "dumb pipe" connectivity, they will increasingly look to leverage partnerships with service providers who can facilitate their own digitalisation on an end-to-end basis. Most of the world's biggest and most ambitious digital transformation champions are looking to sharpen their focus on the Middle East and Africa region.

Worldwide spending on artificial intelligence is expected to reach €40 billion in 2020. Human-centric industries, such as financial services, retail and healthcare are expected to be the biggest spenders, closely followed by asset-intensive industries manufacturing, energy & utility, transport etc.

Atos, a global leader in digital transformation, is taking part in the'Covid-19 Dataset Challenge', an international competition hosted on online community Kaggle[1] asking AI researchers to apply machine learning tools and techniques to help provide answers to key questions about the virus. Atos is deeply involved with a team of 10 experts working on the project, using their AI and automation skills to digest scientific articles and help the medical community to keep up to date with the latest publications on Covid-19. Literature reviews are essential to the research process. They aim to compare and contrast the thinking, ideologies and concepts on a particular subject area. In the specific context of Covid-19, they are essential to the research process as they provide deeper insights, leading to quicker discovery of any gaps in research.