- Deep Learning with PyTorch
- Vishnu Subramanian
- 53字
- 2021-06-24 19:16:27
Tanh
The tanh non-linearity function squashes a real-valued number in the range of -1 and 1. The tanh also faces the same issue of saturating gradients when tanh outputs extreme values close to -1 and 1. However, it is preferred to sigmoid, as the output of tanh is zero centered:
Image source: http://datareview.info/article/eto-nuzhno-znat-klyuchevyie-rekomendatsii-po-glubokomu-obucheniyu-chast-2/
推薦閱讀
- FPGA從入門到精通（實(shí)戰(zhàn)篇）
- The Applied AI and Natural Language Processing Workshop
- 精選單片機(jī)設(shè)計(jì)與制作30例（第2版）
- The Deep Learning with Keras Workshop
- Mastering Adobe Photoshop Elements
- 筆記本電腦維修300問
- 基于Proteus仿真的51單片機(jī)應(yīng)用
- Intel FPGA權(quán)威設(shè)計(jì)指南：基于Quartus Prime Pro 19集成開發(fā)環(huán)境
- UML精粹：標(biāo)準(zhǔn)對(duì)象建模語言簡明指南（第3版）
- 計(jì)算機(jī)組裝、維護(hù)與維修項(xiàng)目教程
- 電腦主板維修技術(shù)
- 新編計(jì)算機(jī)組裝與維護(hù)
- Unreal Engine 4 AI Programming Essentials
- Hands-On Unsupervised Learning with Python
- 數(shù)據(jù)恢復(fù)與硬盤修理