190 citations · 1.5k across the 53 of their papers we have counts for
7 papers · 1 filter
Open-Source Heterogeneous SoCs for AI: The PULP Platform Experience
Francesco Conti, Angelo Garofalo, Davide Rossi +2
Since 2013, the PULP (Parallel Ultra-Low Power) Platform project has been one of the most active and successful initiatives in designing research IPs and releasing them as open-sou…
A Flexible Template for Edge Generative AI with High-Accuracy Accelerated Softmax & GELU
Andrea Belano, Yvan Tortorella, Angelo Garofalo +3
Transformer-based generative Artificial Intelligence (GenAI) models achieve remarkable results in a wide range of fields, including natural language processing, computer vision, an…
Distributed Inference with Minimal Off-Chip Traffic for Transformers on Low-Power MCUs
Severin Bochem, Victor J. B. Jung, Arpan Prasad +2
Contextual Artificial Intelligence (AI) based on emerging Transformer models is predicted to drive the next technology revolution in interactive wearable devices such as new-genera…
Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks
Alberto Dequino, Alessio Carpegna, Davide Nadalini +4
Rehearsal-based Continual Learning (CL) has been intensely investigated in Deep Neural Networks (DNNs). However, its application in Spiking Neural Networks (SNNs) has not been expl…
HTVM: Efficient Neural Network Deployment On Heterogeneous TinyML Platforms
Josse Van Delm, Maarten Vandersteegen, Alessio Burrello +5
Optimal deployment of deep neural networks (DNNs) on state-of-the-art Systems-on-Chips (SoCs) is crucial for tiny machine learning (TinyML) at the edge. The complexity of these SoC…
Multi-resolution Rescored ByteTrack for Video Object Detection on Ultra-low-power Embedded Systems
Luca Bompani, Manuele Rusci, Daniele Palossi +2
This paper introduces Multi-Resolution Rescored Byte-Track (MR2-ByteTrack), a novel video object detection framework for ultra-low-power embedded processors. This method reduces th…
Optimizing the Deployment of Tiny Transformers on Low-Power MCUs
Victor J. B. Jung, Alessio Burrello, Moritz Scherer +2
Transformer networks are rapidly becoming SotA in many fields, such as NLP and CV. Similarly to CNN, there is a strong push for deploying Transformer models at the extreme edge, ul…