skip to main content
paste
bin
.ca
type · paste · share
⌘
K
Family
The bin family
pastebin.ca
hub
Share text and code with expiry and privacy controls.
imagebin.ca
Upload and share images with direct links.
filebin.ca
Drop a file and get a shareable link.
notebin.ca
Write Markdown notes with durable links.
turl.ca
Short, reputation-checked links.
attn.ca
Notifications and alerts for your services.
voicebin.ca
Record and share short voice clips.
dnsbin.ca
Inspect DNS and debug records.
Docs
Sign in
?
← back to paste
›
Edit / fork
Untitled paste
#7cTrUQbfZS
public / public
new version
anonymous
created 2 days ago
Expires in 5 days
669 B
syntax:
text
Your changes create a new paste linked to this one — the original is untouched.
new version
Your changes create a new paste linked to this one — the original is untouched.
Title (optional)
Filename
Syntax
text
text
bash
c
cpp
css
diff
dockerfile
go
html
ini
java
javascript
json
kotlin
lua
makefile
markdown
nginx
php
python
ruby
rust
shellscript
sql
swift
toml
typescript
xml
yaml
Visibility
Public feed
Access
public
Expires
7 days
10 min
1 hour
1 day
7 days
30 days
90 days
custom…
Custom expiry
Change note
(optional)
This paste will be listed on the public feed. Change Visibility if you only want people with the link to see it.
Create new version
Cancel
Paste or type…
神经网络依靠非线性激活函数(GELU/ReLU等),可以自动从原始输入学习高阶非线性组合,自动拟合复杂映射关系,不需要人工构造多项式特征;传统线性回归模型本身是线性的,必须手动增加高次项才能拟合非线性。 以 y=x^2+2x 为例,神经网络如何在不人工构造x^2的情况下学到这个非线性关系? 网络通过多层线性变换+GELU非线性激活的叠加,等价构造出高阶多项式映射。输入x经过线性层加权求和,再经过GELU非线性变换,多层叠加后,网络参数自动学习出等价于 x^2+2x 的非线性映射,自动拟合目标函数。