most citedAn affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms

17 citations

9 papers

cs.AI2026

Leveraging systems' non-linearity to tackle the scarcity of data in the design of Intelligent Fault Diagnosis Systems

Giancarlo Santamato, Andrea Mattia Garavagno, Massimiliano Solazzi +1

Deep Transfer Learning (DTL) allows for the efficient building of Intelligent Fault Diagnosis Systems (IFDS). On the other hand, DTL methods still heavily rely on large amounts of…

cs.IT2026

Nonlinearity Compensation for Coherent Optical Satellite Communications

Stella Civelli, Luca Potì, Enrico Forestieri +1

Optical satellite uplinks rely on high-power optical amplifiers (HPOAs) to overcome free-space attenuation and enable long-distance transmission. However, at high power levels, fib…

cs.LG20264 cited

Searching Neural Architectures for Sensor Nodes on IoT Gateways

Andrea Mattia Garavagno, Edoardo Ragusa, Antonio Frisoli +1

This paper presents an automatic method for the design of Neural Networks (NNs) at the edge, enabling Machine Learning (ML) access even in privacy-sensitive Internet of Things (IoT…

cs.CV202614 cited

Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor

Andrea Mattia Garavagno, Daniele Leonardis, Antonio Frisoli

The current trend of applying transfer learning from convolutional neural networks (CNNs) trained on large datasets can be an overkill when the target application is a custom and d…

cs.LG202617 cited

An affordable hardware-aware neural architecture search for deploying convolutional neural networks on ultra-low-power computing platforms

Andrea Mattia Garavagno, Edoardo Ragusa, Antonio Frisoli +1

Hardware-aware neural architecture search (HW-NAS) allows the integration of Convolutional Neural Networks (CNNs) in microcontrollers devices by automatically designing neural arch…

cs.LG20261 cited

On-Device Neural Architecture Search

Andrea Mattia Garavagno, Edoardo Ragusa, Paolo Gastaldo +2

This paper proposes a new approach to near-sensor computing, in which a lightweight Neural Architecture Search (NAS) is performed directly on the deployment device to find the best…