Session

DescriptionThis special session aims to discuss various approaches to neuromorphic computing for edge AI applications focusing on emerging technologies, novel architectures and sensing modalities to enhance perception. We will have an introductory tutorial dedicated to current strategies to achieve low-power computing at the Edge based on CMOS and post-CMOS technologies. Then, we will focus on limitations of current solutions and introduce four different strategies to overcome such limitations in the remaining talks. These talks are related to four European projects funded under the same call entitled “Ultra-low-power,
secure processors for edge computing”. These projects aiming at reducing by two orders of magnitude current energy consumptions and with budgets between 8 and 10 million Euros gather a large number of academic and industrial key European players on computing technologies. The second talk discusses design strategies in the CONVOLVE project for SoCs dedicated to edge AI applications by taking a holistic approach to design space exploration. Trade-offs tackling the whole tool chain will be presented to achieve substantial improvements in energy consumptions. The third talk discusses the neuromorphic approach taken in the NimbleAI project combining a vertebrate eye-inspired foveated DVS chip
coupled with an insect eye-inspired microlens array to sense and process light fields at different resolutions with minimal latency and energy consumption. The final talk discusses the development of neuromorphic accelerators based on integrated photonics in the NEUROPULS project. Photonic architectures leveraging phase-change and III-V materials for neuromorphic computing will be presented. We expect this session to foster opportunities to link these initiatives at the EU level with similar initiatives worldwide.