咨询与建议

限定检索结果

文献类型

  • 1 篇 期刊文献

馆藏范围

  • 1 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 1 篇 工学
    • 1 篇 计算机科学与技术...
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 1 篇 dynamic activati...
  • 1 篇 second order alg...
  • 1 篇 orthogonal least...
  • 1 篇 output weight op...

机构

  • 1 篇 univ texas arlin...
  • 1 篇 northwestern uni...
  • 1 篇 carnegie mellon ...

作者

  • 1 篇 rane chinmay
  • 1 篇 tyagi kanishka
  • 1 篇 manry michael
  • 1 篇 chugh tushar
  • 1 篇 kline adrienne

语言

  • 1 篇 英文
检索条件"主题词=Dynamic activation functions"
1 条 记 录,以下是1-10 订阅
排序:
Optimizing performance of feedforward and convolutional neural networks through dynamic activation functions
收藏 引用
EVOLUTIONARY INTELLIGENCE 2024年 第5-6期17卷 4083-4093页
作者: Rane, Chinmay Tyagi, Kanishka Kline, Adrienne Chugh, Tushar Manry, Michael Univ Texas Arlington Dept Elect Engn Arlington TX 76019 USA Northwestern Univ Ctr Artificial Intelligence Div Cardiac Surg Northwestern Med Chicago IL 60201 USA Carnegie Mellon Univ Sch Comp Sci Pittsburgh PA 15213 USA
Training algorithms in the domain of deep learning, have led to significant breakthroughs across diverse and subsequent domains including speech, text, images, and video processing. While the research around deeper ne... 详细信息
来源: 评论