1,721,062 research outputs found
Qui a tué Ajax, fils de Telamón ? De la double mort d'un héros et d'autres incohérences dans la tradition troyenne
No full textBarbieri Luca. Qui a tué Ajax, fils de Telamón ? De la double mort d'un héros et d'autres incohérences dans la tradition troyenne. In: Romania, tome 123 n°491-492, 2005. pp. 321-359
A Compressed Decentralized Federated Learning Framework for Enhanced Environmental Awareness in V2V Networks
No full textA Layer Selection Optimizer for Communication-Efficient Decentralized Federated Deep Learning
Full text linkFederated Learning (FL) systems orchestrate the cooperative training of a shared Machine Learning (ML) model across connected devices. Recently, decentralized FL architectures driven by consensus have been proposed to enable the devices to share and aggregate the ML model parameters via direct sidelink communications. The approach has the advantage of promoting the federation among the agents even in the absence of a server, but may require an intensive use of communication resources compared to vanilla FL methods. This paper proposes a communication-efficient design of consensus-driven FL optimized for training of Deep Neural Networks (DNNs). Devices independently select fragments of the DNN to be shared with neighbors on each training round. Selection is based on a local optimizer that trades model quality improvement with sidelink communication resource savings. The proposed technique is validated on a vehicular cooperative sensing use case characterized by challenging real-world datasets and complex DNNs typically employed in autonomous driving with up to 40 trainable layers. The impact of layer selection is analyzed under different distributed coordination configurations. The results show that it is better to prioritize the DNN layers possessing few parameters, while the selection policy should optimally balance gradient sorting and randomization. Latency, accuracy and communication tradeoffs are analyzed in detail targeting sustainable federation policies
A Layer-Wise Personalization Approach for Transformer-Based Federated Anomaly Detection
No full textPersonalized Federated Learning (PFL) tools have been recently applied in Anomaly Detection (AD) setups to accurately monitor complex industrial systems under data heterogeneity while complying with strict privacy regulations. PFL techniques integrating transformer models in AD setups are still overlooked even though they provide outstanding performances that are hardly matched by other Neural Network (NN) architectures. This paper thus focuses on developing transformer-based PFL techniques in AD contexts to improve AD accuracy under data heterogeneity. Specifically, we propose decoupling the FL optimization process in a layer-wise manner by carefully selecting which model fragments are learned collaboratively and which are personalized (i.e., trained without cooperation). We refer to our proposed methodology as Layer-Wise Personalized FL (LPFL). The developed approach is evaluated with four design choices for selecting the model layers tailored according to the peculiar architecture of transformer NNs (e.g., the self-attention mechanism). Experimental results on four widely-adopted AD datasets highlight that the self-attention mechanism should always be learned collaboratively while all other trainable parameters should be personalized. Adopting such a choice boosts AD accuracy and reduces the communication overhead by up to 16% and 52%, respectively, compared to other personalization choices, standard FL policies, and individual training strategies
Compressed Bayesian Federated Learning for Reliable Passive Radio Sensing in Industrial IoT
No full textBayesian Federated Learning (FL) has been recently introduced to provide well-calibrated Machine Learning (ML) models quantifying the uncertainty of their predictions. Despite their advantages compared to frequentist FL setups, Bayesian FL tools implemented over decentralized networks are subject to high communication costs due to the iterated exchange of local posterior distributions among cooperating devices. Therefore, this paper proposes a communication-efficient decentralized Bayesian FL policy to reduce the communication overhead without sacrificing final learning accuracy and calibration. The proposed method integrates compression policies and allows devices to perform multiple optimization steps before sending the local posterior distributions. We integrate the developed tool in an Industrial Internet of Things (IIoT) use case where collaborating nodes equipped with autonomous radar sensors are tasked to reliably localize human operators in a workplace shared with robots. Numerical results show that the developed approach obtains highly accurate yet well-calibrated ML models compatible with the ones provided by conventional (uncompressed) Bayesian FL tools while substantially decreasing the communication overhead (i.e., up to 99%). Furthermore, the proposed approach is advantageous when compared with state-of-the-art compressed frequentist FL setups in terms of calibration, especially when the statistical distribution of the testing dataset changes
Ascolto come esperienza: effetti, presenza, corporeità in un videoclip dance
No full textCosa accade musiche da ballo sono trasferite su video, se cioè un brano musicale diventa un videoclip? Diventa una categoria di testi che cerca di porre il fruitore all’interno del testo, e non più semplicemente davanti al testo. Testi-performance che intendono produrre effetti in grado di generare una forma di esperienza di tipo immersivo, tramite una razionalità impressiva. Le ritmicità del brano dance, ovvero quelle potenzialità sonore che all’ascolto acusmatico in assenza del video sono in grado di indurre il ballo, vengono tradotte sul piano visivo innescando una vera e propria forma di continua risemantizzazione tra le due forme espressive, visiva e sonora una modalità audiovisiva concepita per ottenere effetti tramite il sincretismo del linguaggio. Del resto un’esperienza ‘dal vivo’, come quella di un concerto, contiene elementi residui densi, difficilmente descrivibili, testualizzabili, e riproducibili in quanto tali. Da questo punto di vista la finzionalità del linguaggio audiovisivo è in grado di generare, paradossalmente, un’autenticità maggiore di quella di una diretta televisiva. Ciò avviene grazie allo sviluppo di un discorso, come quello del videoclip, che, se ben adoperato, non rappresenta un surrogato della realtà ma ne produce semplicemente un’altra. L’analisi dell’enunciazione audiovisiva è in grado di indicarcene dettagliatamente le motivazioni, a partire dalla sincresi audiovisiva che diventa meccanismo di costruzione di presenza
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
