当前位置:网站首页>End to end neural network
End to end neural network
2022-07-05 12:26:00 【Nat_ Jst】
When learning neural networks , I often see in the paper that , This network is end-to-end Of ,end-to-end Refers to what kind of network ?
End to end means that the input is raw data , The output is the final result , The original input is not the direct raw data , It's a feature extracted from the raw data , This is particularly prominent in the image problem , Because there are too many pixels in the image , High data dimension , There will be dimensional disasters , So the original idea is to manually extract some key features of the image , This is actually a dimensionality reduction process .
So here comes the question , How to mention features ? The quality of feature extraction is extremely critical , Even more important than learning algorithms , for instance , Data classification of a series of people , The classification result is gender , If the feature you extract is the color of your hair , No matter how the classification algorithm , The classification effect will not be good , If the feature you extract is the length of hair , This feature will be much better , But there will still be mistakes , If you extract a super feature , For example, chromosome data , Then your classification will not be wrong . That means , Features need enough experience to design , This is becoming more and more difficult with the increasing amount of data . So it came out End to end networks , Characteristics can be learned by yourself , So feature extraction is integrated into the algorithm , No need for human intervention .
end-to-end The essence of is that the problem you want to solve is multi-stage or multi-step ( With the so-called raw feature Do not have what relation ). If you study in stages , The optimal solution in the first stage can not guarantee the optimization of the problem in the second stage .end-to-end Put them together to optimize , Ensure that the solution in the final stage is optimal .
The advantage is convenience .
The disadvantage is that it is more and more like a black box .
边栏推荐
- Multi table operation - Auto Association query
- Course design of compilation principle --- formula calculator (a simple calculator with interface developed based on QT)
- Learn the memory management of JVM 03 - Method area and meta space of JVM
- About cache exceptions: solutions for cache avalanche, breakdown, and penetration
- Summary of C language learning problems (VS)
- mysql拆分字符串做条件查询
- byte2String、string2Byte
- MySQL basic operation -dql
- Swift - enables textview to be highly adaptive
- How can beginners learn flutter efficiently?
猜你喜欢
ZABBIX ODBC database monitoring
Embedded software architecture design - message interaction
自动化测试生命周期
MySQL transaction
How to clear floating?
Seven ways to achieve vertical centering
Learn the memory management of JVM 02 - memory allocation of JVM
MySQL storage engine
The evolution of mobile cross platform technology
A guide to threaded and asynchronous UI development in the "quick start fluent Development Series tutorials"
随机推荐
Average lookup length when hash table lookup fails
MySQL data table operation DDL & data type
Time tools
Learn the memory management of JVM 03 - Method area and meta space of JVM
Flutter2 heavy release supports web and desktop applications
Learn JVM garbage collection 05 - root node enumeration, security points, and security zones (hotspot)
Differences between IPv6 and IPv4 three departments including the office of network information technology promote IPv6 scale deployment
How to recover the information server and how to recover the server data [easy to understand]
Conversion du format de données GPS [facile à comprendre]
[untitled]
Linux Installation and deployment lamp (apache+mysql+php)
Xi IO flow
Check the debug port information in rancher and do idea remote JVM debug
MySQL installation, Windows version
SENT协议译码的深入探讨
Semantic segmentation experiment: UNET network /msrc2 dataset
Automated test lifecycle
Design of music box based on assembly language
Codeworks 5 questions per day (1700 average) - day 5
July Huaqing learning-1