Impact of ML optimization tactics on greener pre-trained ML models

AG Álvarez, J Castaño, X Franch… - ar** Review on Quantization Methods for Medical Imaging AI
AR Paddo, RT Raju, JW Gichoya… - … on Biomedical Imaging …, 2024 - ieeexplore.ieee.org
Deep neural networks with state-of-the-art (SOTA) performance on medical imaging
datasets such as Medical Resonance Imaging (MRI), Ultrasound (US), and Computed …

Exploiting neural networks bit-level redundancy to mitigate the impact of faults at inference

I Catalán, J Flich, C Hernández - The Journal of Supercomputing, 2025 - Springer
Neural networks are widely used in critical environments such as healthcare, autonomous
vehicles, or video surveillance. To ensure the safety of the systems that rely on their …

Towards Efficient Neural Network Model Parallelism on Multi-FPGA Platforms

DR Agut, R Tornero, J Flich - … & Test in Europe Conference & …, 2023 - ieeexplore.ieee.org
Nowadays, convolutional neural networks (CNN) are common in a wide range of
applications. Their high accuracy and efficiency contrast with their computing requirements …

A round-trip journey in pruned artificial neural networks

A Bragagnolo, E Tartaglione, G Dalmasso… - CEUR WORKSHOP …, 2023 - iris.unito.it
In the last decade, deep learning models competed for performance at the price of
tremendous computational costs. Such a critical aspect recently attracted more attention for …

[PDF][PDF] Exploring the Design and Implementation of Pruning Techniques for Deep Neural Networks

A Bragagnolo - 2023 - iris.unito.it
Deep neural networks have become one of the go-to tools to achieve state-of-the-art
performance for various tasks, such as computer vision, speech recognition, and many …

[CITAS][C] HPC Platform for Railway Safety-Critical Functionalities Based on Artificial Intelligence

M Labayen Esnaola, L Medina, F Eizaguirre, J Flich… - 2023 - MDPI