118 citations · 485 across the 63 of their papers we have counts for
28 papers · 1 filter
MAUPITI: On-Device Prototype-Based Learning on a Smart Infrared Sensor
Beatrice Alessandra Motetti, Tanguy Dugas du Villard, Matteo Risso +7
Low-resolution infrared (IR) array sensors represent an interesting solution for privacy-preserving human sensing in embedded systems. In this letter, we describe a smart multi-pix…
End-to-end Automated Deep Neural Network Optimization for PPG-based Blood Pressure Estimation on Wearables
Francesco Carlucci, Giovanni Pollo, Xiaying Wang +6
Photoplethysmography (PPG)-based blood pressure (BP) estimation is a challenging task, particularly on resource-constrained wearable devices. However, fully on-board processing is…
Don't be so Stief! Learning KV Cache low-rank approximation over the Stiefel manifold
Luca Benfenati, Matteo Risso, Andrea Vannozzi +5
Key-value (KV) caching enables fast autoregressive decoding but at long contexts becomes a dominant bottleneck in High Bandwidth Memory (HBM) capacity and bandwidth. A common mitig…
V-Seek: Accelerating LLM Reasoning on Open-hardware Server-class RISC-V Platforms
Javier J. Poveda Rodrigo, Mohamed Amine Ahmdi, Alessio Burrello +2
The recent exponential growth of Large Language Models (LLMs) has relied on GPU-based systems. However, CPUs are emerging as a flexible and lower-cost alternative, especially when…
Lightweight Software Kernels and Hardware Extensions for Efficient Sparse Deep Neural Networks on Microcontrollers
Francesco Daghero, Daniele Jahier Pagliari, Francesco Conti +3
The acceleration of pruned Deep Neural Networks (DNNs) on edge devices such as Microcontrollers (MCUs) is a challenging task, given the tight area- and power-constraints of these d…
Coupling Neural Networks and Physics Equations For Li-Ion Battery State-of-Charge Prediction
Giovanni Pollo, Alessio Burrello, Enrico Macii +3
Estimating the evolution of the battery's State of Charge (SoC) in response to its usage is critical for implementing effective power management policies and for ultimately improvi…
Optimizing DNN Inference on Multi-Accelerator SoCs at Training-time
Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari
The demand for executing Deep Neural Networks (DNNs) with low latency and minimal power consumption at the edge has led to the development of advanced heterogeneous Systems-on-Chip…
Deeploy: Enabling Energy-Efficient Deployment of Small Language Models On Heterogeneous Microcontrollers
Moritz Scherer, Luka Macan, Victor Jung +5
With the rise of Embodied Foundation Models (EFMs), most notably Small Language Models (SLMs), adapting Transformers for edge applications has become a very active field of researc…
Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networks
Beatrice Alessandra Motetti, Matteo Risso, Alessio Burrello +3
The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mi…
BISeizuRe: BERT-Inspired Seizure Data Representation to Improve Epilepsy Monitoring
Luca Benfenati, Thorir Mar Ingolfsson, Andrea Cossettini +3
This study presents a novel approach for EEG-based seizure detection leveraging a BERT-based model. The model, BENDR, undergoes a two-phase training process. Initially, it is pre-t…
Accelerating Depthwise Separable Convolutions on Ultra-Low-Power Devices
Francesco Daghero, Alessio Burrello, Massimo Poncino +2
Depthwise separable convolutions are a fundamental component in efficient Deep Neural Networks, as they reduce the number of parameters and operations compared to traditional convo…
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…
Foundation Models for Structural Health Monitoring
Luca Benfenati, Daniele Jahier Pagliari, Luca Zanatta +6
Structural Health Monitoring (SHM) is a critical task for ensuring the safety and reliability of civil infrastructures, typically realized on bridges and viaducts by means of vibra…
HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays
Matteo Risso, Chen Xie, Francesco Daghero +6
Low-resolution infrared (IR) array sensors enable people counting applications such as monitoring the occupancy of spaces and people flows while preserving privacy and minimizing e…
Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices
Alessio Burrello, Matteo Risso, Beatrice Alessandra Motetti +3
The rapid proliferation of computing domains relying on Internet of Things (IoT) devices has created a pressing need for efficient and accurate deep-learning (DL) models that can r…
PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization
Daniele Jahier Pagliari, Matteo Risso, Beatrice Alessandra Motetti +1
Accurate yet efficient Deep Neural Networks (DNNs) are in high demand, especially for applications that require their execution on constrained edge devices. Finding such DNNs in a…
Dynamic Decision Tree Ensembles for Energy-Efficient Inference on IoT Edge Nodes
Francesco Daghero, Alessio Burrello, Enrico Macii +3
With the increasing popularity of Internet of Things (IoT) devices, there is a growing need for energy-efficient Machine Learning (ML) models that can run on constrained edge nodes…
Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inference
Matteo Risso, Alessio Burrello, Giuseppe Maria Sarda +5
The need to execute Deep Neural Networks (DNNs) at low latency and low power at the edge has spurred the development of new heterogeneous Systems-on-Chips (SoCs) encapsulating a di…
Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge
Matteo Risso, Alessio Burrello, Francesco Conti +6
Neural Architecture Search (NAS) is quickly becoming the go-to approach to optimize the structure of Deep Learning (DL) models for complex tasks such as Image Classification or Obj…
Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks
Francesco Daghero, Alessio Burrello, Chen Xie +6
Human Activity Recognition (HAR) based on inertial data is an increasingly diffused task on embedded devices, from smartphones to ultra low-power sensors. Due to the high computati…
Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes
Matteo Risso, Alessio Burrello, Luca Benini +3
Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks. In particular, mixed-precis…
Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks
Matteo Risso, Alessio Burrello, Luca Benini +3
Neural Architecture Search (NAS) is increasingly popular to automatically explore the accuracy versus computational complexity trade-off of Deep Learning (DL) architectures. When t…
Adaptive Random Forests for Energy-Efficient Inference on Microcontrollers
Francesco Daghero, Alessio Burrello, Chen Xie +5
Random Forests (RFs) are widely used Machine Learning models in low-power embedded devices, due to their hardware friendly operation and high accuracy on practically relevant tasks…
Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors
Francesco Daghero, Chen Xie, Daniele Jahier Pagliari +6
Human Activity Recognition (HAR) is a relevant inference task in many mobile applications. State-of-the-art HAR at the edge is typically achieved with lightweight machine learning…