Výsledky vyhledávání - "Malchiodi,Dario"

Report

Support Vector Based Anomaly Detection in Federated Learning

Autor: Frasson, Massimo, Malchiodi, Dario

Anomaly detection plays a crucial role in various domains, from cybersecurity to industrial systems. However, traditional centralized approaches often encounter challenges related to data privacy. In this context, Federated Learning emerges as a prom

Externí odkaz: http://arxiv.org/abs/2407.03920

Zobrazit plný text záznamu

Report

A Critical Analysis of Classifier Selection in Learned Bloom Filters

Autor: Malchiodi, Dario, Raimondi, Davide, Fumagalli, Giacomo, Giancarlo, Raffaele, Frasca, Marco

Learned Bloom Filters, i.e., models induced from data via machine learning techniques and solving the approximate set membership problem, have recently been introduced with the aim of enhancing the performance of standard Bloom Filters, with special

Externí odkaz: http://arxiv.org/abs/2211.15565

Zobrazit plný text záznamu

Report

On the Choice of General Purpose Classifiers in Learned Bloom Filters: An Initial Analysis Within Basic Filters

Autor: Fumagalli, Giacomo, Raimondi, Davide, Giancarlo, Raffaele, Malchiodi, Dario, Frasca, Marco

Bloom Filters are a fundamental and pervasive data structure. Within the growing area of Learned Data Structures, several Learned versions of Bloom Filters have been considered, yielding advantages over classic Filters. Each of them uses a classifier

Externí odkaz: http://arxiv.org/abs/2112.06563

Zobrazit plný text záznamu

Report

Compact representations of convolutional neural networks via weight pruning and quantization

Autor: Marinò, Giosuè Cataldo, Petrini, Alessandro, Malchiodi, Dario, Frasca, Marco

The state-of-the-art performance for several real-world problems is currently reached by convolutional neural networks (CNN). Such learning models exploit recent results in the field of deep learning, typically leading to highly performing, yet very

Externí odkaz: http://arxiv.org/abs/2108.12704

Zobrazit plný text záznamu

Report

Compression strategies and space-conscious representations for deep neural networks

Autor: Marinò, Giosuè Cataldo, Ghidoli, Gregorio, Frasca, Marco, Malchiodi, Dario

Recent advances in deep learning have made available large, powerful convolutional neural networks (CNN) with state-of-the-art performance in several real-world applications. Unfortunately, these large-sized models have millions of parameters, thus t

Externí odkaz: http://arxiv.org/abs/2007.07967

Zobrazit plný text záznamu