Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Daniele Di Sarli"'
Publikováno v:
Computer Science and Information System
In the context of recurrent neural networks, gated architectures such as the GRU have contributed to the development of highly accurate machine learning models that can tackle long-term dependencies in the data. However, the training of such networks
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::0f4ff5a281b5750b468e5397d63842e7
http://hdl.handle.net/11568/1135130
http://hdl.handle.net/11568/1135130
Autor:
Christos Sardianos, Davide Bacciu, Vincenzo Lomonaco, Pietro Cassara, Siranush Akarmazyan, Manlio Bacco, Jürgen Dobaj, Omar Veledar, Claudio Gallicchio, Georg Macher, Alessio Micheli, Patrizio Dazzi, Rosaria Potenza, Fulvio Tagliabo, Daniele Di Sarli, Konstantinos Tserpes, Charalampos Davalas, Massimo Coppola, Maria Carmela Degennaro, Calogero Calandra, Jakob Valtl, Dimitrios Michail, Salvatore Petroni, Iraklis Varlamis, George Bravos, Roberta Peroglio, Daniele Mazzei, Eric Armengaud, Gabriele Mencagli, Farank Pourdanesh, Alberto Gotta, Sylvain Girbal, Emanuele Carlini, Riccardo Groppo, Antonio Carta
Publikováno v:
IEEE COINS 2021-IEEE International Conference on Omni-layer Intelligent systems, Online conference, 23-26/08/2021
info:cnr-pdr/source/autori:Bacciu D.; Akarmazyan S.; Armengaud E.; Bacco M.; Bravos G.; Calandra C.; Carlini E.; Carta A.; Cassarà P.; Coppola M.; Davalas C.; Dazzi P.; Degennaro M.C.; Di Sarli D.; Dobaj J.; Gallicchio C.; Girbal S.; Gotta A.; Groppo R.; Lomonaco V.; Macher G.; Mazzei D.; Mencagli G.; Michail D.; Micheli A.; Peroglio R.; Petroni S.; Potenza R.; Pourdanesh F.; Sardianos C.; Tserpes K.; Tagliabò F.; Vatl J.; Varlamis I.; Veledar O./congresso_nome:IEEE COINS 2021-IEEE International Conference on Omni-layer Intelligent systems/congresso_luogo:Online conference/congresso_data:23-26%2F08%2F2021/anno:2021/pagina_da:/pagina_a:/intervallo_pagine
COINS
info:cnr-pdr/source/autori:Bacciu D.; Akarmazyan S.; Armengaud E.; Bacco M.; Bravos G.; Calandra C.; Carlini E.; Carta A.; Cassarà P.; Coppola M.; Davalas C.; Dazzi P.; Degennaro M.C.; Di Sarli D.; Dobaj J.; Gallicchio C.; Girbal S.; Gotta A.; Groppo R.; Lomonaco V.; Macher G.; Mazzei D.; Mencagli G.; Michail D.; Micheli A.; Peroglio R.; Petroni S.; Potenza R.; Pourdanesh F.; Sardianos C.; Tserpes K.; Tagliabò F.; Vatl J.; Varlamis I.; Veledar O./congresso_nome:IEEE COINS 2021-IEEE International Conference on Omni-layer Intelligent systems/congresso_luogo:Online conference/congresso_data:23-26%2F08%2F2021/anno:2021/pagina_da:/pagina_a:/intervallo_pagine
COINS
This paper discusses the perspective of the H2020 TEACHING project on the next generation of autonomous applications running in a distributed and highly heterogeneous environment comprising both virtual and physical resources spanning the edge-cloud
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7455eaf46b31da63b07723db5cfc1a6c
https://publications.cnr.it/doc/455251
https://publications.cnr.it/doc/455251
Publikováno v:
INISTA
2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)
2020 International Conference on INnovations in Intelligent SysTems and Applications (INISTA)
Gating mechanisms are widely used in the context of Recurrent Neural Networks (RNNs) to improve the network's ability to deal with long-term dependencies within the data. The typical approach for training such networks involves the expensive algorith
Recurrent Neural Networks (RNNs) represent a natural paradigm for modeling sequential data like text written in natural language. In fact, RNNs and their variations have long been the architecture of choice in many applications, however in practice t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bcce7bece8f9012044840ea2eca41626
http://hdl.handle.net/11568/1072922
http://hdl.handle.net/11568/1072922
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030351656
AI*IA
AI*IA
Recurrent Neural Networks (RNNs) are at the foundation of many state-of-the-art results in text classification. However, to be effective in practical applications, they often require the use of sophisticated architectures and training techniques, suc
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c193fbb85363b76c0e27e9794fe1ef37
https://doi.org/10.1007/978-3-030-35166-3_26
https://doi.org/10.1007/978-3-030-35166-3_26
Autor:
Filippo Geraci, Daniele Di Sarli
Publikováno v:
International Conference on Information System and Data Mining (ICISDM 2017), Charleston, South Carolina, USA, 01-03/04/2017
info:cnr-pdr/source/autori:D. Di Sarli, F. Geraci/congresso_nome:International Conference on Information System and Data Mining (ICISDM 2017)/congresso_luogo:Charleston, South Carolina, USA/congresso_data:01-03%2F04%2F2017/anno:2017/pagina_da:/pagina_a:/intervallo_pagine
info:cnr-pdr/source/autori:D. Di Sarli, F. Geraci/congresso_nome:International Conference on Information System and Data Mining (ICISDM 2017)/congresso_luogo:Charleston, South Carolina, USA/congresso_data:01-03%2F04%2F2017/anno:2017/pagina_da:/pagina_a:/intervallo_pagine
Organizing documents in the file system is one of the most tedious and thorny tasks for most computer users. Taxonomies based on hand made directory hierarchies still remain the only possible alternative for most small and medium enterprises, public
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bde1d5589187a37815da23c930fc7ac6
http://www.cnr.it/prodotto/i/371379
http://www.cnr.it/prodotto/i/371379
Publikováno v:
2021 International Joint Conference on Neural Networks (IJCNN)
IJCNN
IJCNN
A critical aspect in Federated Learning is the aggregation strategy for the combination of multiple models, trained on the edge, into a single model that incorporates all the knowledge in the federation. Common Federated Learning approaches for Recur
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::955fd48fef78be810898b83b05c7720a
Autor:
Davide Bacciu, Antonio Carta, Daniele Di Sarli, Claudio Gallicchio, Vincenzo Lomonaco, Salvatore Petroni
Publikováno v:
Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy
Deploying Autonomous Driving systems requires facing some novel challenges for the Automotive industry. One of the most critical aspects that can severely compromise their de- ployment is Functional Safety. The ISO 26262 standard provides guidelines
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c740bcb67529ab2c701cb4461e312f4e
Publikováno v:
Scopus-Elsevier
EVALITA Evaluation of NLP and Speech Tools for Italian ISBN: 9788831978422
EVALITA@CLiC-it
EVALITA Evaluation of NLP and Speech Tools for Italian ISBN: 9788831978422
EVALITA@CLiC-it
For the “ITAmoji” EVALITA 2018 competition we mainly exploit a Reservoir Computing approach to learning, with an ensemble of models for trees and sequences. The sentences for the models of the former kind are processed by a language parser and th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::05efd7d43196fd78c7cd1818ec92e04e
http://www.scopus.com/inward/record.url?eid=2-s2.0-85058635842&partnerID=MN8TOARS
http://www.scopus.com/inward/record.url?eid=2-s2.0-85058635842&partnerID=MN8TOARS