Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Haasbroek, Daniël G."'
Autor:
Mouton, Coenraad, Rabe, Randle, Haasbroek, Daniël G., Theunissen, Marthinus W., Potgieter, Hermanus L., Davel, Marelie H.
It has been observed that the input space of deep neural network classifiers can exhibit `fragmentation', where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation tends to follow the double de
Externí odkaz:
http://arxiv.org/abs/2411.04695
Each node in a neural network is trained to activate for a specific region in the input domain. Any training samples that fall within this domain are therefore implicitly clustered together. Recent work has highlighted the importance of these cluster
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1399::a8c3816d07f3d503d2edc14069171d3c
https://hdl.handle.net/10394/36796
https://hdl.handle.net/10394/36796