Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Zullich, Marco"'
Modelling uncertainty in Machine Learning models is essential for achieving safe and reliable predictions. Most research on uncertainty focuses on output uncertainty (predictions), but minimal attention is paid to uncertainty at inputs. We propose a
Externí odkaz:
http://arxiv.org/abs/2406.18787
Autor:
ZULLICH, MARCO
La potatura, nel contesto dell'Apprendimento Automatico, denota l'atto di rimuovere parametri da modelli parametrici come modelli lineari, alberi decisionali e Reti Neurali Artificiali (ANN). La potatura di un modello può essere motivata da numerose
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::7cead676979cee8614bb384fc59dc657
https://hdl.handle.net/11368/3041099
https://hdl.handle.net/11368/3041099
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Zullich, Marco
Publikováno v:
IEEE Access. IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
In Late-Medieval panel paintings from the Tuscan area, mechanical tools called punches were used to impress repeated motifs on gold foils to create decorative patterns. Such patterns can be used as clues to objectively support the attribution of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=narcis______::007101b75f1415a160232694e4c8b287
https://research.rug.nl/en/publications/a663f1cf-0933-47d8-b091-8dff5c14f44a
https://research.rug.nl/en/publications/a663f1cf-0933-47d8-b091-8dff5c14f44a
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Nadizar, Giorgia, Medvet, Eric, Huse Ramstad, Ola, Nichele, Stefano, Pellegrino, Felice Andrea, Zullich, Marco
Publikováno v:
Knowledge Engineering Review; 2022, Vol. 37, p1-1, 1p
In Late-Medieval panel paintings from the Tuscan area, mechanical tools called punches were used to impress repeated motifs on gold foils to create decorative patterns. Such patterns can be used as clues to objectively support the attribution of the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e8c3625a7158cd42c41379b97c49d1c
https://hdl.handle.net/11368/3038944
https://hdl.handle.net/11368/3038944
Merging pruning and neuroevolution: towards robust and efficient controllers for modular soft robots
Autor:
Giorgia Nadizar, Eric Medvet, Hola Huse Ramstad, Stefano Nichele, Felice Andrea Pellegrino, Marco Zullich
Publikováno v:
Knowledge engineering review
e3
e3
Artificial neural networks (ANNs) can be employed as controllers for robotic agents. Their structure is often complex, with many neurons and connections, especially when the robots have many sensors and actuators distributed across their bodies and/o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cd9789536a36828452d38aec674f62e6
https://hdl.handle.net/11250/3040433
https://hdl.handle.net/11250/3040433
Autor:
Benedetta Liberatori, Ciro Antonio Mami, Giovanni Santacatterina, Marco Zullich, Felice Andrea Pellegrino
Deploying Deep Learning (DL) based object detection (OD) models in low-end devices, such as single board computers, may lead to poor performance in terms of frames-per-second (FPS). Pruning and quantization are well-known compression techniques that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::195933916f31e3c13773b493796f032c
http://hdl.handle.net/11368/3028994
http://hdl.handle.net/11368/3028994