dAIEDGE will participate in the upcoming HiPEAC Conference, one of the most prestigious European platforms for technological debate and advancement, which will take place next week, from 20-22 January 2025 in Barcelona (Spain).
Workshops organised and co-organised by dAIEDGE
- Workshop Excellence in AI and Edge Computing, which will be held on Monday, 20 January, from 10:00 to 17:30
The convergence of AI and edge computing represents a new era of technological advances, where the immediacy of data processing and the sophistication of AI algorithms lead to new products and services. Industries are rapidly adopting edge AI applications to streamline costs, automate complex processes, enhance decision-making capabilities, and refine operational efficiency. These applications are not just theoretical constructs; they are real-world solutions that are reshaping industries.
This workshop is dedicated to exploring the frontiers of the AI and edge computing synergy, focusing on the development of scalable and robust AI systems. In order to make the workshop more interactive and lively, there will be a matchmaking session and a demo session. In the latter, participants will be able to show live demos, either on-site or with a video, of their research and results. Participants in any session will be automatically invited to participate in and benefit from dAIEdge’s network of excellence.
- Workshop on Charting the future, which will be held on Tuesday, 21 January, from 10:00 to 17:30
The workshop organised by Alain Pagani Project Coordinator of dAIEDGE in collaboration with Ovidiu Vermesan will address how edge AI technologies refer to a transformative AI approach that combines IoT and edge computing. In this approach, data processing and computing occurs at the ‘edge’, closer to the data source and end users, rather than relying exclusively on centralised processing services. This paradigm shift enables a number of innovative capabilities and advantages, making it especially significant in scenarios that require real-time or near-real-time data processing and decision-making.
As generative AI continues to evolve and develop the ability to create innovative solutions in various domains, the integration of edge computing becomes increasingly important. This workshop brings together experts and stakeholders to explore the functional and non-functional requirements for the effective deployment of edge AI technologies, taking into account the evolution of generative AI applications.
Functional requirements for peripheral AI systems address the identification and definition of core functionalities essential for deploying peripheral AI models, ensuring real-time data processing and decision-making capabilities, and exploring hardware and software design considerations for efficient peripheral AI inference.
Discussions on non-functional requirements will focus on system quality properties to ensure reliability, robustness, dependability, security, availability, explainability and interpretability in peripheral AI systems, while ensuring their scalability and adaptability to support diverse environments and workloads.
The workshop will provide a comprehensive platform for stakeholders to exchange ideas, share experiences and collaborate on advancing cutting-edge AI technologies. By addressing functional and non-functional requirements defined based on systems engineering principles, participants will gain valuable insights on deploying effective and accountable edge AI solutions using cross-disciplinary approaches to enhance edge AI capabilities in the era of generative AI.
The workshop combines presentations and panel discussions to enable participants to share their ideas, research results and best practices, facilitating a collaborative environment that promotes innovation in edge AI.
- We will also participate in the Accelerated Machine Learning (AccML) workshop, to be held on Tuesday 21 January, from 10:00 to 17:30.
This workshop organised by the University of Glasgow and Google aims to analyse the remarkable performance achieved in a variety of application areas (natural language processing, computer vision, gaming, etc.) that has led to the emergence of heterogeneous architectures for accelerating machine learning workloads. In parallel, production deployment, model complexity and diversity pushed for higher productivity systems, more powerful programming abstractions, software and system architectures, dedicated runtime systems and numerical libraries, deployment and analysis tools. Deep learning models are generally memory and computationally intensive, for both training and inference. Accelerating these operations has obvious advantages, first by reducing the energy consumption (e.g. in data centers), and secondly, making these models usable on smaller devices at the edge of the Internet. In addition, while convolutional neural networks have motivated much of this effort, numerous applications and models involve a wider variety of operations, network architectures, and data processing. These applications and models permanently challenge computer architecture, the system stack, and programming abstractions.
The workshop brings together researchers and practitioners working on computing systems for machine learning, and using machine learning to build better computing systems. It also reaches out to a wider community interested in this rapidly growing area, to raise awareness of the existing efforts, to foster collaboration and the free exchange of ideas.
Come and meet us at our stand!
In addition to the workshops, during the three days of the event we will be present at stand 23, where attendees will be able to learn in detail about our projects and use cases, discover how we are positioning Europe as a world leader in the data economy, and interact directly with us.