tinyML Talks on November 28, 2023 “tinyML: Designing Efficient Neural Architectures and Scaling Strategies for Edge Computing” by Francesco Paissan from Fondazione Bruno Kessler

We held our next tinyML Talks webcast. Francesco Paissan from Fondazione Bruno Kessler presented tinyML: Designing Efficient Neural Architectures and Scaling Strategies for Edge Computing on November 28, 2023.

In the Internet of Things (IoT) era, where we see many interconnected and heterogeneous mobile and fixed smart devices, distributing intelligence from the cloud to the edge has become critical for the sustainability of the infrastructures and comes with additional benefits (e.g. power efficiency, low-latency inference, privacy-by-design) with respect to centralized cloud computing. This paradigm brings new challenges in deep learning, such as low memory availability and limited energy budget. In this seminar, we will discuss some of our recent efforts to tackle the challenges of tinyML with novel neural architectures, training paradigms, and scaling strategies. In particular, we will focus on efficient multimedia analytics pipelines that achieve state-of-the-art results with a fraction of the computational budget of competitive approaches. Among the practical applications of these novel methodologies, we will discuss their performance for object detection, tracking, and zero-shot audio classification.

Francesco Paissan has been a Junior Researcher in the Energy Efficient Embedded Digital Architectures (E3DA) unit in Fondazione Bruno Kessler (FBK) since 2018. His research interests include diverse topics, from developing and modelling scalable neural architectures for multimedia analytics to bio-signals analysis with deep learning architectures. In 2021, Francesco joined the LEGEND experiment for the design of novel physics-inspired ML algorithms (e.g. learning-based triggering logics for cosmogenic rejection in the experiment’s veto). Francesco was a research intern at the Montreal Institute of Learning Algorithms (Mila) in Montreal, where he worked on post-hoc interpretability techniques for neural networks. WWW speaker: https://francescopaissan.it/


Download presentation slides:
Francesco Paissan

Watch on YouTube:
Francesco Paissan

Feel free to ask your questions on this thread and keep the conversation going!