Search Results for author: Daniele Jahier Pagliari

Found 31 papers, 12 papers with code

Optimizing Foundation Model Inference on a Many-tiny-core Open-source RISC-V Platform

no code implementations29 May 2024 Viviane Potocnik, Luca Colagrande, Tim Fischer, Luca Bertaccini, Daniele Jahier Pagliari, Alessio Burrello, Luca Benini

For decoder-only topologies, we achieve 16. 1x speedup in the Non-Autoregressive (NAR) mode and up to 35. 6x speedup in the Autoregressive (AR) mode compared to the baseline implementation.

Decoder

Integrating SystemC-AMS Power Modeling with a RISC-V ISS for Virtual Prototyping of Battery-operated Embedded Devices

1 code implementation2 Apr 2024 Mohamed Amine Hamdi, Giovanni Pollo, Matteo Risso, Germain Haugou, Alessio Burrello, Enrico Macii, Massimo Poncino, Sara Vinco, Daniele Jahier Pagliari

The combination of GVSoC and SystemC-AMS in a single simulation framework allows to perform a DSE that is dependent on the mutual impact between functional and extra-functional aspects.

Optimized Deployment of Deep Neural Networks for Visual Pose Estimation on Nano-drones

no code implementations23 Feb 2024 Matteo Risso, Francesco Daghero, Beatrice Alessandra Motetti, Daniele Jahier Pagliari, Enrico Macii, Massimo Poncino, Alessio Burrello

Miniaturized autonomous unmanned aerial vehicles (UAVs) are gaining popularity due to their small size, enabling new tasks such as indoor navigation or people monitoring.

Neural Architecture Search Pose Estimation

HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays

no code implementations2 Feb 2024 Matteo Risso, Chen Xie, Francesco Daghero, Alessio Burrello, Seyedmorteza Mollaei, Marco Castellano, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

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 energy consumption.

Neural Architecture Search Privacy Preserving +1

Adaptive Deep Learning for Efficient Visual Pose Estimation aboard Ultra-low-power Nano-drones

no code implementations26 Jan 2024 Beatrice Alessandra Motetti, Luca Crupi, Mustafa Omer Mohammed Elamin Elshaigi, Matteo Risso, Daniele Jahier Pagliari, Daniele Palossi, Alessio Burrello

Sub-10cm diameter nano-drones are gaining momentum thanks to their applicability in scenarios prevented to bigger flying drones, such as in narrow environments and close to humans.

Computational Efficiency Pose Estimation

Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devices

2 code implementations11 Oct 2023 Alessio Burrello, Matteo Risso, Beatrice Alessandra Motetti, Enrico Macii, Luca Benini, Daniele Jahier Pagliari

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 run on low-power devices.

Neural Architecture Search

PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization

1 code implementation18 Jul 2023 Daniele Jahier Pagliari, Matteo Risso, Beatrice Alessandra Motetti, Alessio Burrello

Accurate yet efficient Deep Neural Networks (DNNs) are in high demand, especially for applications that require their execution on constrained edge devices.

Dynamic Decision Tree Ensembles for Energy-Efficient Inference on IoT Edge Nodes

1 code implementation16 Jun 2023 Francesco Daghero, Alessio Burrello, Enrico Macii, Paolo Montuschi, Massimo Poncino, Daniele Jahier Pagliari

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.

C++ code

Precision-aware Latency and Energy Balancing on Multi-Accelerator Platforms for DNN Inference

1 code implementation8 Jun 2023 Matteo Risso, Alessio Burrello, Giuseppe Maria Sarda, Luca Benini, Enrico Macii, Massimo Poncino, Marian Verhelst, Daniele Jahier Pagliari

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 diverse set of hardware accelerators.

Quantization

Energy-efficient Wearable-to-Mobile Offload of ML Inference for PPG-based Heart-Rate Estimation

no code implementations8 Jun 2023 Alessio Burrello, Matteo Risso, Noemi Tomasello, Yukai Chen, Luca Benini, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

In this work, we propose a collaborative inference approach that uses both a smartwatch and a connected smartphone to maximize the performance of heart rate (HR) tracking while also maximizing the smartwatch's battery life.

Collaborative Inference Heart rate estimation

Efficient Deep Learning Models for Privacy-preserving People Counting on Low-resolution Infrared Arrays

no code implementations12 Apr 2023 Chen Xie, Francesco Daghero, Yukai Chen, Marco Castellano, Luca Gandolfi, Andrea Calimera, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

Ultra-low-resolution Infrared (IR) array sensors offer a low-cost, energy-efficient, and privacy-preserving solution for people counting, with applications such as occupancy monitoring.

Privacy Preserving

Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs

no code implementations3 Mar 2023 Elia Cereda, Luca Crupi, Matteo Risso, Alessio Burrello, Luca Benini, Alessandro Giusti, Daniele Jahier Pagliari, Daniele Palossi

In this work, we leverage a novel neural architecture search (NAS) technique to automatically identify several Pareto-optimal convolutional neural networks (CNNs) for a visual pose estimation task.

Neural Architecture Search Pose Estimation

Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edge

1 code implementation24 Jan 2023 Matteo Risso, Alessio Burrello, Francesco Conti, Lorenzo Lamberti, Yukai Chen, Luca Benini, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

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 Object Detection.

Image Classification Neural Architecture Search +4

Human Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks

no code implementations2 Sep 2022 Francesco Daghero, Alessio Burrello, Chen Xie, Marco Castellano, Luca Gandolfi, Andrea Calimera, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

With experiments on four datasets, and targeting an ultra-low-power RISC-V MCU, we show that (i) We are able to obtain a rich set of Pareto-optimal CNNs for HAR, spanning more than 1 order of magnitude in terms of memory, latency and energy consumption; (ii) Thanks to adaptive inference, we can derive >20 runtime operating modes starting from a single CNN, differing by up to 10% in classification scores and by more than 3x in inference complexity, with a limited memory overhead; (iii) on three of the four benchmarks, we outperform all previous deep learning methods, reducing the memory occupation by more than 100x.

Human Activity Recognition Quantization

Channel-wise Mixed-precision Assignment for DNN Inference on Constrained Edge Nodes

1 code implementation17 Jun 2022 Matteo Risso, Alessio Burrello, Luca Benini, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

Quantization is widely employed in both cloud and edge systems to reduce the memory occupation, latency, and energy consumption of deep neural networks.

Neural Architecture Search Quantization

Two-stage Human Activity Recognition on Microcontrollers with Decision Trees and CNNs

no code implementations7 Jun 2022 Francesco Daghero, Daniele Jahier Pagliari, Massimo Poncino

In this work, we bridge the gap between on-device HAR and DL thanks to a hierarchical architecture composed of a decision tree (DT) and a one dimensional Convolutional Neural Network (1D CNN).

Human Activity Recognition

Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks

1 code implementation1 Jun 2022 Matteo Risso, Alessio Burrello, Luca Benini, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

When deployed on a commercial edge device, the STM NUCLEO-H743ZI2, our networks span a range of 2. 18x in energy consumption and 4. 04% in accuracy for the same memory constraint, and reduce energy by up to 2. 2x with negligible accuracy drop with respect to the baseline.

Neural Architecture Search

Adaptive Random Forests for Energy-Efficient Inference on Microcontrollers

no code implementations27 May 2022 Francesco Daghero, Alessio Burrello, Chen Xie, Luca Benini, Andrea Calimera, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

The accuracy of a RF often increases with the number of internal weak learners (decision trees), but at the cost of a proportional increase in inference latency and energy consumption.

Ultra-compact Binary Neural Networks for Human Activity Recognition on RISC-V Processors

1 code implementation25 May 2022 Francesco Daghero, Chen Xie, Daniele Jahier Pagliari, Alessio Burrello, Marco Castellano, Luca Gandolfi, Andrea Calimera, Enrico Macii, Massimo Poncino

In this work, we propose a novel implementation of HAR based on deep neural networks, and precisely on Binary Neural Networks (BNNs), targeting low-power general purpose processors with a RISC-V instruction set.

Human Activity Recognition

Privacy-preserving Social Distance Monitoring on Microcontrollers with Low-Resolution Infrared Sensors and CNNs

no code implementations22 Apr 2022 Chen Xie, Francesco Daghero, Yukai Chen, Marco Castellano, Luca Gandolfi, Andrea Calimera, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

In this work, we demonstrate that an accurate detection of social distance violations can be achieved processing the raw output of a 8x8 IR array sensor with a small-sized Convolutional Neural Network (CNN).

Privacy Preserving

Energy-efficient and Privacy-aware Social Distance Monitoring with Low-resolution Infrared Sensors and Adaptive Inference

no code implementations22 Apr 2022 Chen Xie, Daniele Jahier Pagliari, Andrea Calimera

Low-resolution infrared (IR) Sensors combined with machine learning (ML) can be leveraged to implement privacy-preserving social distance monitoring solutions in indoor spaces.

Privacy Preserving

C-NMT: A Collaborative Inference Framework for Neural Machine Translation

no code implementations8 Apr 2022 Yukai Chen, Roberta Chiaro, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

Collaborative Inference (CI) optimizes the latency and energy consumption of deep learning inference through the inter-operation of edge and cloud devices.

Collaborative Inference Machine Translation +2

Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence

no code implementations7 Apr 2022 Francesco Daghero, Alessio Burrello, Daniele Jahier Pagliari, Luca Benini, Enrico Macii, Massimo Poncino

Energy-efficient machine learning models that can run directly on edge devices are of great interest in IoT applications, as they can reduce network pressure and response latency, and improve privacy.

BIG-bench Machine Learning

Robust and Energy-efficient PPG-based Heart-Rate Monitoring

no code implementations28 Mar 2022 Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari, Simone Benatti, Enrico Macii, Luca Benini, Massimo Poncino

A wrist-worn PPG sensor coupled with a lightweight algorithm can run on a MCU to enable non-invasive and comfortable monitoring, but ensuring robust PPG-based heart-rate monitoring in the presence of motion artifacts is still an open challenge.

Neural Architecture Search

Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices

1 code implementation24 Mar 2022 Alessio Burrello, Daniele Jahier Pagliari, Matteo Risso, Simone Benatti, Enrico Macii, Luca Benini, Massimo Poncino

Our most accurate quantized network achieves 4. 41 Beats Per Minute (BPM) of Mean Absolute Error (MAE), with an energy consumption of 47. 65 mJ and a memory footprint of 412 kB.

Neural Architecture Search Photoplethysmography (PPG)

Cannot find the paper you are looking for? You can Submit a new open access paper.