Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Luca Benini

Luca Benini

Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering


Apr 29, 2022
Thorir Mar Ingolfsson, Mark Vero, Xiaying Wang, Lorenzo Lamberti, Luca Benini, Matteo Spallanzani

Figure 1 for Reducing Neural Architecture Search Spaces with Training-Free Statistics and Computational Graph Clustering

  Access Paper or Ask Questions

Energy-Efficient Tree-Based EEG Artifact Detection


Apr 19, 2022
Thorir Mar Ingolfsson, Andrea Cossettini, Simone Benatti, Luca Benini

Figure 1 for Energy-Efficient Tree-Based EEG Artifact Detection
Figure 2 for Energy-Efficient Tree-Based EEG Artifact Detection
Figure 3 for Energy-Efficient Tree-Based EEG Artifact Detection
Figure 4 for Energy-Efficient Tree-Based EEG Artifact Detection
* 6 pages, 3 figures, 2 tables 
  Access Paper or Ask Questions

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


Apr 07, 2022
Francesco Daghero, Alessio Burrello, Daniele Jahier Pagliari, Luca Benini, Enrico Macii, Massimo Poncino

Figure 1 for Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence
Figure 2 for Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence
Figure 3 for Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence
Figure 4 for Energy-Efficient Adaptive Machine Learning on IoT End-Nodes With Class-Dependent Confidence
* 2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS), 2020, pp. 1-4 
 * Published in: 2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS) 
  Access Paper or Ask Questions

Constrained Few-shot Class-incremental Learning


Mar 30, 2022
Michael Hersche, Geethan Karunaratne, Giovanni Cherubini, Luca Benini, Abu Sebastian, Abbas Rahimi

Figure 1 for Constrained Few-shot Class-incremental Learning
Figure 2 for Constrained Few-shot Class-incremental Learning
Figure 3 for Constrained Few-shot Class-incremental Learning
Figure 4 for Constrained Few-shot Class-incremental Learning
* CVPR 2022 camera-ready version 
  Access Paper or Ask Questions

MI-BMInet: An Efficient Convolutional Neural Network for Motor Imagery Brain--Machine Interfaces with EEG Channel Selection


Mar 29, 2022
Xiaying Wang, Michael Hersche, Michele Magno, Luca Benini

Figure 1 for MI-BMInet: An Efficient Convolutional Neural Network for Motor Imagery Brain--Machine Interfaces with EEG Channel Selection
Figure 2 for MI-BMInet: An Efficient Convolutional Neural Network for Motor Imagery Brain--Machine Interfaces with EEG Channel Selection
Figure 3 for MI-BMInet: An Efficient Convolutional Neural Network for Motor Imagery Brain--Machine Interfaces with EEG Channel Selection
Figure 4 for MI-BMInet: An Efficient Convolutional Neural Network for Motor Imagery Brain--Machine Interfaces with EEG Channel Selection

  Access Paper or Ask Questions

Leveraging Tactile Sensors for Low Latency Embedded Smart Hands for Prosthetic and Robotic Applications


Mar 28, 2022
Xiaying Wang, Fabian Geiger, Vlad Niculescu, Michele Magno, Luca Benini

Figure 1 for Leveraging Tactile Sensors for Low Latency Embedded Smart Hands for Prosthetic and Robotic Applications
Figure 2 for Leveraging Tactile Sensors for Low Latency Embedded Smart Hands for Prosthetic and Robotic Applications
Figure 3 for Leveraging Tactile Sensors for Low Latency Embedded Smart Hands for Prosthetic and Robotic Applications
Figure 4 for Leveraging Tactile Sensors for Low Latency Embedded Smart Hands for Prosthetic and Robotic Applications
* arXiv admin note: substantial text overlap with arXiv:2107.14598 
  Access Paper or Ask Questions

Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks


Mar 28, 2022
Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari, Francesco Conti, Lorenzo Lamberti, Enrico Macii, Luca Benini, Massimo Poncino

Figure 1 for Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
Figure 2 for Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
Figure 3 for Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
Figure 4 for Pruning In Time (PIT): A Lightweight Network Architecture Optimizer for Temporal Convolutional Networks
* 2021 58th ACM/IEEE Design Automation Conference (DAC), 2021, pp. 1015-1020 
  Access Paper or Ask Questions

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


Mar 28, 2022
Matteo Risso, Alessio Burrello, Daniele Jahier Pagliari, Simone Benatti, Enrico Macii, Luca Benini, Massimo Poncino

Figure 1 for Robust and Energy-efficient PPG-based Heart-Rate Monitoring
Figure 2 for Robust and Energy-efficient PPG-based Heart-Rate Monitoring
Figure 3 for Robust and Energy-efficient PPG-based Heart-Rate Monitoring
Figure 4 for Robust and Energy-efficient PPG-based Heart-Rate Monitoring
* 2021 IEEE International Symposium on Circuits and Systems (ISCAS), 2021, pp. 1-5 
  Access Paper or Ask Questions

Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition


Mar 25, 2022
Alessio Burrello, Francesco Bianco Morghet, Moritz Scherer, Simone Benatti, Luca Benini, Enrico Macii, Massimo Poncino, Daniele Jahier Pagliari

Figure 1 for Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition
Figure 2 for Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition
Figure 3 for Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition
Figure 4 for Bioformers: Embedding Transformers for Ultra-Low Power sEMG-based Gesture Recognition

  Access Paper or Ask Questions

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


Mar 24, 2022
Alessio Burrello, Daniele Jahier Pagliari, Matteo Risso, Simone Benatti, Enrico Macii, Luca Benini, Massimo Poncino

Figure 1 for Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices
Figure 2 for Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices
Figure 3 for Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices
Figure 4 for Q-PPG: Energy-Efficient PPG-based Heart Rate Monitoring on Wearable Devices

  Access Paper or Ask Questions

TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference


Mar 24, 2022
Alessio Burrello, Alberto Dequino, Daniele Jahier Pagliari, Francesco Conti, Marcello Zanghieri, Enrico Macii, Luca Benini, Massimo Poncino

Figure 1 for TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
Figure 2 for TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
Figure 3 for TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
Figure 4 for TCN Mapping Optimization for Ultra-Low Power Time-Series Edge Inference
* 2021 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED) 
  Access Paper or Ask Questions

Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm


Mar 21, 2022
Matteo Spallanzani, Gian Paolo Leonardi, Luca Benini

Figure 1 for Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
Figure 2 for Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
Figure 3 for Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm
Figure 4 for Training Quantised Neural Networks with STE Variants: the Additive Noise Annealing Algorithm

  Access Paper or Ask Questions

Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring


Mar 10, 2022
Amirhossein Moallemi, Alessio Burrello, Davide Brunelli, Luca Benini

Figure 1 for Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring
Figure 2 for Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring
Figure 3 for Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring
Figure 4 for Exploring Scalable, Distributed Real-Time Anomaly Detection for Bridge Health Monitoring
* 14 pages, 5 tables, 12 figures 
  Access Paper or Ask Questions

A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices


Mar 09, 2022
Michael Hersche, Mustafa Zeqiri, Luca Benini, Abu Sebastian, Abbas Rahimi

Figure 1 for A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices
Figure 2 for A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices
Figure 3 for A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices
Figure 4 for A Neuro-vector-symbolic Architecture for Solving Raven's Progressive Matrices

  Access Paper or Ask Questions

Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring


Mar 01, 2022
Alessio Burrello, Daniele Jahier Pagliari, Pierangelo Maria Rapa, Matilde Semilia, Matteo Risso, Tommaso Polonelli, Massimo Poncino, Luca Benini, Simone Benatti

Figure 1 for Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring
Figure 2 for Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring
Figure 3 for Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring
Figure 4 for Embedding Temporal Convolutional Networks for Energy-Efficient PPG-Based Heart Rate Monitoring

  Access Paper or Ask Questions

Vau da muntanialas: Energy-efficient multi-die scalable acceleration of RNN inference


Feb 14, 2022
Gianna Paulin, Francesco Conti, Lukas Cavigelli, Luca Benini

* IEEE Transactions on Circuits and Systems I: Regular Papers, IEEE, Volume: 69, Issue: 1, January 2022, Date of Publication (Early Access) 30 July 2021 
  Access Paper or Ask Questions

Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks


Jan 10, 2022
Gianmarco Cerutti, Lukas Cavigelli, Renzo Andri, Michele Magno, Elisabetta Farella, Luca Benini

Figure 1 for Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks
Figure 2 for Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks
Figure 3 for Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks
Figure 4 for Sub-mW Keyword Spotting on an MCU: Analog Binary Feature Extraction and Binary Neural Networks

  Access Paper or Ask Questions

A Heterogeneous In-Memory Computing Cluster For Flexible End-to-End Inference of Real-World Deep Neural Networks


Jan 04, 2022
Angelo Garofalo, Gianmarco Ottavi, Francesco Conti, Geethan Karunaratne, Irem Boybat, Luca Benini, Davide Rossi

Figure 1 for A Heterogeneous In-Memory Computing Cluster For Flexible End-to-End Inference of Real-World Deep Neural Networks
Figure 2 for A Heterogeneous In-Memory Computing Cluster For Flexible End-to-End Inference of Real-World Deep Neural Networks
Figure 3 for A Heterogeneous In-Memory Computing Cluster For Flexible End-to-End Inference of Real-World Deep Neural Networks
Figure 4 for A Heterogeneous In-Memory Computing Cluster For Flexible End-to-End Inference of Real-World Deep Neural Networks
* 14 pages (not including final biography page), 13 figures (excluded authors pictures) 
  Access Paper or Ask Questions

Sub-100uW Multispectral Riemannian Classification for EEG-based Brain--Machine Interfaces


Dec 18, 2021
Xiaying Wang, Lukas Cavigelli, Tibor Schneider, Luca Benini

Figure 1 for Sub-100uW Multispectral Riemannian Classification for EEG-based Brain--Machine Interfaces
Figure 2 for Sub-100uW Multispectral Riemannian Classification for EEG-based Brain--Machine Interfaces
Figure 3 for Sub-100uW Multispectral Riemannian Classification for EEG-based Brain--Machine Interfaces
Figure 4 for Sub-100uW Multispectral Riemannian Classification for EEG-based Brain--Machine Interfaces

  Access Paper or Ask Questions

A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays


Oct 20, 2021
Leonardo Ravaglia, Manuele Rusci, Davide Nadalini, Alessandro Capotondi, Francesco Conti, Luca Benini

Figure 1 for A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays
Figure 2 for A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays
Figure 3 for A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays
Figure 4 for A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays
* 14 pages 
  Access Paper or Ask Questions

Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode


Oct 18, 2021
Davide Rossi, Francesco Conti, Manuel Eggimann, Alfio Di Mauro, Giuseppe Tagliavini, Stefan Mach, Marco Guermandi, Antonio Pullini, Igor Loi, Jie Chen, Eric Flamand, Luca Benini

Figure 1 for Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode
Figure 2 for Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode
Figure 3 for Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode
Figure 4 for Vega: A 10-Core SoC for IoT End-Nodes with DNN Acceleration and Cognitive Wake-Up From MRAM-Based State-Retentive Sleep Mode
* 13 pages, 11 figures, 8 tables, journal paper 
  Access Paper or Ask Questions

A Fully-Integrated 5mW, 0.8Gbps Energy-Efficient Chip-to-Chip Data Link for Ultra-Low-Power IoT End-Nodes in 65-nm CMOS


Sep 05, 2021
Hayate Okuhara, Ahmed Elnaqib, Martino Dazzi, Pierpaolo Palestri, Simone Benatti, Luca Benini, Davide Rossi

Figure 1 for A Fully-Integrated 5mW, 0.8Gbps Energy-Efficient Chip-to-Chip Data Link for Ultra-Low-Power IoT End-Nodes in 65-nm CMOS
Figure 2 for A Fully-Integrated 5mW, 0.8Gbps Energy-Efficient Chip-to-Chip Data Link for Ultra-Low-Power IoT End-Nodes in 65-nm CMOS
Figure 3 for A Fully-Integrated 5mW, 0.8Gbps Energy-Efficient Chip-to-Chip Data Link for Ultra-Low-Power IoT End-Nodes in 65-nm CMOS
Figure 4 for A Fully-Integrated 5mW, 0.8Gbps Energy-Efficient Chip-to-Chip Data Link for Ultra-Low-Power IoT End-Nodes in 65-nm CMOS

  Access Paper or Ask Questions

Memory-Aware Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems


Aug 05, 2021
Andres Gomez, Andreas Tretter, Pascal Alexander Hager, Praveenth Sanmugarajah, Luca Benini, Lothar Thiele

Figure 1 for Memory-Aware Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems
Figure 2 for Memory-Aware Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems
Figure 3 for Memory-Aware Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems
Figure 4 for Memory-Aware Partitioning of Machine Learning Applications for Optimal Energy Use in Batteryless Systems

  Access Paper or Ask Questions

SmartHand: Towards Embedded Smart Hands for Prosthetic and Robotic Applications


Jul 23, 2021
Xiaying Wang, Fabian Geiger, Vlad Niculescu, Michele Magno, Luca Benini

Figure 1 for SmartHand: Towards Embedded Smart Hands for Prosthetic and Robotic Applications
Figure 2 for SmartHand: Towards Embedded Smart Hands for Prosthetic and Robotic Applications
Figure 3 for SmartHand: Towards Embedded Smart Hands for Prosthetic and Robotic Applications
Figure 4 for SmartHand: Towards Embedded Smart Hands for Prosthetic and Robotic Applications

  Access Paper or Ask Questions

DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors


Jul 16, 2021
Enrico Tabanelli, Giuseppe Tagliavini, Luca Benini

Figure 1 for DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors
Figure 2 for DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors
Figure 3 for DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors
Figure 4 for DNN is not all you need: Parallelizing Non-Neural ML Algorithms on Ultra-Low-Power IoT Processors

  Access Paper or Ask Questions

NN2CAM: Automated Neural Network Mapping for Multi-Precision Edge Processing on FPGA-Based Cameras


Jun 24, 2021
Petar Jokic, Stephane Emery, Luca Benini

Figure 1 for NN2CAM: Automated Neural Network Mapping for Multi-Precision Edge Processing on FPGA-Based Cameras
Figure 2 for NN2CAM: Automated Neural Network Mapping for Multi-Precision Edge Processing on FPGA-Based Cameras
Figure 3 for NN2CAM: Automated Neural Network Mapping for Multi-Precision Edge Processing on FPGA-Based Cameras
Figure 4 for NN2CAM: Automated Neural Network Mapping for Multi-Precision Edge Processing on FPGA-Based Cameras

  Access Paper or Ask Questions

A Construction Kit for Efficient Low Power Neural Network Accelerator Designs


Jun 24, 2021
Petar Jokic, Erfan Azarkhish, Andrea Bonetti, Marc Pons, Stephane Emery, Luca Benini

Figure 1 for A Construction Kit for Efficient Low Power Neural Network Accelerator Designs
Figure 2 for A Construction Kit for Efficient Low Power Neural Network Accelerator Designs
Figure 3 for A Construction Kit for Efficient Low Power Neural Network Accelerator Designs
Figure 4 for A Construction Kit for Efficient Low Power Neural Network Accelerator Designs

  Access Paper or Ask Questions

Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices


Jun 17, 2021
Thorir Mar Ingolfsson, Andrea Cossettini, Xiaying Wang, Enrico Tabanelli, Giuseppe Tagliavini, Philippe Ryvlin, Luca Benini, Simone Benatti

Figure 1 for Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices
Figure 2 for Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices
Figure 3 for Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices
Figure 4 for Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices
* 4 pages, 3 figures, 2 tables, preprint 
  Access Paper or Ask Questions

Trimming Feature Extraction and Inference for MCU-based Edge NILM: a Systematic Approach


May 21, 2021
Enrico Tabanelli, Davide Brunelli, Andrea Acquaviva, Luca Benini

Figure 1 for Trimming Feature Extraction and Inference for MCU-based Edge NILM: a Systematic Approach
Figure 2 for Trimming Feature Extraction and Inference for MCU-based Edge NILM: a Systematic Approach
Figure 3 for Trimming Feature Extraction and Inference for MCU-based Edge NILM: a Systematic Approach
Figure 4 for Trimming Feature Extraction and Inference for MCU-based Edge NILM: a Systematic Approach
* Transactions on Industrial Informatics (2021) 
  Access Paper or Ask Questions

Structural Health Monitoring system with Narrowband IoT and MEMS sensors


Apr 27, 2021
Flavio Di Nuzzo, Davide Brunelli, Tommaso Polonelli, Luca Benini

Figure 1 for Structural Health Monitoring system with Narrowband IoT and MEMS sensors
Figure 2 for Structural Health Monitoring system with Narrowband IoT and MEMS sensors
Figure 3 for Structural Health Monitoring system with Narrowband IoT and MEMS sensors
Figure 4 for Structural Health Monitoring system with Narrowband IoT and MEMS sensors
* 10 pages, 10 figures, IEEE Sensors Journal 
  Access Paper or Ask Questions