Ferro4EdgeAI
Scalable, Ferroelectric-based Accelerators for Energy Efficient Edge Artificial Intelligence
—————
Ferroelectric edge processor technology for speech recognition is a new approach to speech processing that utilises ferroelectric hafnia to create highly efficient and low-power processors. These processors can be embedded directly into devices, such as smartphones, smart speakers, and wearables, enabling real-time speech recognition without the need for cloud connectivity.
Ultra-low power, scalable edge accelerator.
The project aims to develop an ultra-low power, scalable edge accelerator. Our innovative solution incorporates a memory-augmented neural network, based on low cost, high density, multi-level, Back End of Line (BEoL) integrated ferroelectric (FE) technology.
Ferro4EdgeAI harnesses the potential of FE technology, leveraging its non-volatile properties and spontaneous polarisation. Through optimised FeFET-2 devices, our consortium partners brings a range of expertise across the entire value chain, from device technology to prototypes and systems simulations. The goal is to maximise the advantages of FE technology, including reliability, durability, high energy efficiency, low latency, and scalability.
The Project
-
About Ferro4EdgeAI
Ferro4EdgeAI is a 4 year project, launched on the 1 January 2024. With 12 leading international research institutions and industrialists in microelectronics and cross-sector partners from 6 countries, the project is committed to developing an ultra-low power, scalable Edge accelerator for AI.
-
Objectives
Discover the project’s five specific objecives and how each project partner is involved in the value chain, starting from materials optimisation, running through devices design and characterisation, array integration to accelerator prototype and finally specific AI systems.
-
Project Partners
Ferro4EdgeAI brings together twelve European partners spanning from six different countries, all who are contributing with expertise from across the entire value chain, from e.g. device technology to prototypes, centred on maximising the advantages of the technology.
Improving the capabilities and efficiency of Edge AI technologies, paving the way for more sophisticated and energy-efficient devices.
Publications
Dive into the world of Ferro4EdgeAI through our comprehensive collection of public deliverables, publications, press releases, newsletters and other promotional materials. Here, you will be able to find detailed reports, and updates about our research in ferroelectric-based accelerators for Edge AI. Our library showcases our work towards achieving a 2500x gain in energy efficiency, breaking new grounds in AI hardware technology.
News
Stay up to date with Ferro4EdgeAI and the latest developments, breakthroughs, and events in the world of Edge AI. Our news section is your go-to source for all project updates, including press mentions, achievements, milestones, and upcoming events. Join our community and be a part of the conversation shaping the future of energy-efficient Edge AI.
Our Partners
