咨询与建议

限定检索结果

文献类型

  • 2 篇 期刊文献
  • 1 篇 会议

馆藏范围

  • 3 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 3 篇 工学
    • 2 篇 计算机科学与技术...
    • 1 篇 电气工程
    • 1 篇 电子科学与技术(可...
  • 1 篇 理学
    • 1 篇 数学

主题

  • 3 篇 relu functions
  • 2 篇 deep neural netw...
  • 1 篇 gradient descent...
  • 1 篇 mnist classifica...
  • 1 篇 quadratic object...
  • 1 篇 deep learning
  • 1 篇 pattern classifi...
  • 1 篇 secure multi-par...
  • 1 篇 neural nets
  • 1 篇 pid controller
  • 1 篇 activation funct...
  • 1 篇 three-term contr...
  • 1 篇 rapido
  • 1 篇 loss of identifi...
  • 1 篇 gradient methods
  • 1 篇 donsker class
  • 1 篇 optimisation
  • 1 篇 rejuvenating ada...
  • 1 篇 sigmoid function...
  • 1 篇 regression model...

机构

  • 1 篇 technol innovat ...
  • 1 篇 univ paris 01 sa...
  • 1 篇 korea adv inst s...
  • 1 篇 katholieke univ ...

作者

  • 1 篇 kim s.
  • 1 篇 rynkiewicz j.
  • 1 篇 park d. j.
  • 1 篇 sucasas victor
  • 1 篇 nawaz kashif
  • 1 篇 aly abdelrahaman
  • 1 篇 salazar eugenio
  • 1 篇 chang d. e.

语言

  • 3 篇 英文
检索条件"主题词=ReLU functions"
3 条 记 录,以下是1-10 订阅
排序:
Asymptotic statistics for multilayer perceptron with relu hidden units
收藏 引用
NEUROCOMPUTING 2019年 342卷 16-23页
作者: Rynkiewicz, J. Univ Paris 01 SAMM 90 Rue Tolbiac F-75013 Paris France
In numerous tasks, deep networks are state of the art. However, they are still not well understood from a statistical point of view. In this article, we try to contribute to filling this gap, and we consider regressio... 详细信息
来源: 评论
RAPIDO: a rejuvenating adaptive PID-type optimiser for deep neural networks
收藏 引用
ELECTRONICS LETTERS 2019年 第16期55卷 899-901页
作者: Kim, S. Park, D. J. Chang, D. E. Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon 34141 South Korea
The authors present a novel gradient descent algorithm called RAPIDO for deep learning. It adapts over time and performs optimisation using current, past and future information similar to the PID controller. The propo... 详细信息
来源: 评论
Through the Looking-Glass: Benchmarking Secure Multi-party Computation Comparisons for relu's  21st
Through the Looking-Glass: Benchmarking Secure Multi-party C...
收藏 引用
21st International Conference on Cryptology and Network Security (CANS)
作者: Aly, Abdelrahaman Nawaz, Kashif Salazar, Eugenio Sucasas, Victor Technol Innovat Inst Cryptog Res Ctr Abu Dhabi U Arab Emirates Katholieke Univ Leuven Imec COSIC Leuven Belgium
Comparisons or Inequality Tests are an essential building block of Rectified Linear Unit functions (relu's), ever more present in Machine Learning, specifically in Neural Networks. Motivated by the increasing inte... 详细信息
来源: 评论