Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Matan Weksler"'
Publikováno v:
Sensors, Vol 21, Iss 16, p 5599 (2021)
A common technique for compressing a neural network is to compute the k-rank ℓ2 approximation Ak of the matrix A∈Rn×d via SVD that corresponds to a fully connected layer (or embedding layer). Here, d is the number of input neurons in the layer,
Externí odkaz:
https://doaj.org/article/18b56702a14f476393df979512e7125a
Publikováno v:
Sensors
Volume 21
Issue 16
Sensors (Basel, Switzerland)
Sensors, Vol 21, Iss 5599, p 5599 (2021)
Volume 21
Issue 16
Sensors (Basel, Switzerland)
Sensors, Vol 21, Iss 5599, p 5599 (2021)
A common technique for compressing a neural network is to compute the k-rank ℓ2 approximation Ak of the matrix A∈Rn×d via SVD that corresponds to a fully connected layer (or embedding layer). Here, d is the number of input neurons in the layer,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::06c3752290c7e9ad8c06645a96243da2