iT邦幫忙

第 11 屆 iThome 鐵人賽

DAY 22
0
Google Developers Machine Learning

ML Study Jam Journey系列 第 22 篇

Day 22 Art and Science of Machine Learning (cont.)

  • 分享至 

  • xImage
  •  

Neural Networks

Linear Model can be represented as nodes and edges
Non-Linear Transformation (aka Activation Function)

Training

Three common failure modes for gradient descent

  • Gradients can vanish - Use ReLu instead of sigmoid/tanh
  • Gradients can explode - Batch Normalization
  • ReLu layers can die - Lower learning rates

上一篇
Day 21 Art and Science of Machine Learning (cont.)
下一篇
Day 23 Art and Science of Machine Learning (cont.)
系列文
ML Study Jam Journey 共 30 篇
圖片
  熱門推薦
圖片
{{ item.channelVendor }} | {{ item.webinarstarted }} |
{{ formatDate(item.duration) }}
直播中

尚未有邦友留言

立即登入留言