ConvNets with Smooth Adaptive Activation Functions for Regression

Within Neural Networks (NN), the parameters of Adaptive Activation Functions (AAF) control the shapes of activation functions. These parameters are trained along with other parameters in the NN. AAFs have improved performance of Convolutional Neural Networks (CNN) in multiple classification tasks. I...

詳細記述

保存先:
書誌詳細
出版年:Proc Mach Learn Res
主要な著者: Hou, Le, Samaras, Dimitris, Kurc, Tahsin M., Gao, Yi, Saltz, Joel H.
フォーマット: Artigo
言語:Inglês
出版事項: 2017
主題:
Article
オンライン･アクセス:https://ncbi.nlm.nih.gov/pmc/articles/PMC6521876/
https://ncbi.nlm.nih.gov/pubmed/31106299
タグ: タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!

類似資料