Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Marko Zeman"'
Publikováno v:
Neural networks, str. 418-436 : Ilustr., Vol. 161, 2023
COBISS-ID: 26011904
COBISS-ID: 26011904
Soavtorji: Jana Faganeli Pucer, Igor Kononenko, Zoran Bosnić. Bibliografija: str. 435-436. Abstract.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f614e1d48516251093af0932b313b70f
https://plus.cobiss.net/cobiss/si/en/bib/141099267
https://plus.cobiss.net/cobiss/si/en/bib/141099267
Publikováno v:
Uporabna informatika. 30
V mnogih aplikacijah strojnega učenja se novi podatki nenehno zbirajo, npr. v zdravstvenem varstvu, za vremenske napovedi itd. Raziskovalci si pogosto želijo sistem, ki bi omogočal nadaljevalno učenje novih informacij. To je izjemnega pomeni tudi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::717ebe2214048149a84f114ec7ef1e44
https://doi.org/10.31449/upinf.183
https://doi.org/10.31449/upinf.183
Publikováno v:
IJCNN
This paper investigates a combination of the two recently proposed techniques: superposition of multiple neural networks into one and neural network compression. We show that these two techniques can be successfully combined to deliver a great potent
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a499722d2e3bf22b9e403b49ba8a76bb
https://doi.org/10.1109/ijcnn52387.2021.9533602
https://doi.org/10.1109/ijcnn52387.2021.9533602