当前位置:网站首页>Introduction to convolutional neural network
Introduction to convolutional neural network
2022-07-05 05:33:00 【Li Junfeng】
introduce
Using fully connected neural network Handwritten digit recognition A high accuracy has been achieved , But this can be improved .
First, let's look at the problems of fully connected neural networks : It ignores structure , When inputting pictures into neural network , It directly converts it into a column , Ignore the relationship between pixels and other pixels in position .
In this simple handwritten numeral recognition , Ignoring this structural relationship can still maintain a good accuracy , But for more complex image recognition , Ignoring this structural relationship often leads to poor results . Therefore, a new neural network is needed to solve this problem .
Convolutional neural networks
Convolutional neural networks (Convolutional Neural Networks, CNN) It is a kind of feedforward neural network with convolution calculation and depth structure (Feedforward Neural Networks), It's deep learning (deep learning) One of the representative algorithms of .
The difference with full connection
Compared with full connection , Convolutional neural networks use Convolution layer And Pooling layer Process the features of the image , Then output the result with full connection .
Convolution layer needs to learn parameters , Convolution check with different parameters, different images will make different responses .
The pooling layer does not need to learn parameters , Generally speaking, it takes the maximum value or average value . But the existence of pooling layer can greatly increase the robustness of neural network , Because even if there are some small changes , It has little effect on the output of the pooling layer .
Why still use full connection
Because in most cases , We don't know the relationship between these parameters , And full connection provides a good platform .
It assumes that all parameters are related , Through constant learning , The edge power of some relationships will continue to grow , It shows that this relationship is real ; But the edge power of some relationships will continue to decrease , It shows that this relationship does not exist or is very weak , It won't have much impact on the final result .
边栏推荐
- Animation scoring data analysis and visualization and it industry recruitment data analysis and visualization
- 搭建完数据库和网站后.打开app测试时候显示服务器正在维护.
- 【实战技能】非技术背景经理的技术管理
- lxml.etree.XMLSyntaxError: Opening and ending tag mismatch: meta line 6 and head, line 8, column 8
- Introduction to memory layout of FVP and Juno platforms
- R语言【数据集的导入导出】
- Talking about JVM (frequent interview)
- Pointnet++ learning
- YOLOv5添加注意力机制
- A misunderstanding about the console window
猜你喜欢
【Jailhouse 文章】Jailhouse Hypervisor
[interval problem] 435 Non overlapping interval
Gbase database helps the development of digital finance in the Bay Area
剑指 Offer 06.从头到尾打印链表
On-off and on-off of quality system construction
YOLOv5-Shufflenetv2
Acwing 4300. Two operations
【实战技能】非技术背景经理的技术管理
Reader writer model
Introduction to tools in TF-A
随机推荐
R语言【数据集的导入导出】
Add level control and logger level control of Solon logging plug-in
[merge array] 88 merge two ordered arrays
Sword finger offer 05 Replace spaces
Animation scoring data analysis and visualization and it industry recruitment data analysis and visualization
Haut OJ 1347: addition of choice -- high progress addition
Demonstration of using Solon auth authentication framework (simpler authentication framework)
lxml. etree. XMLSyntaxError: Opening and ending tag mismatch: meta line 6 and head, line 8, column 8
Add level control and logger level control of Solon logging plug-in
Cluster script of data warehouse project
Pointnet++ learning
剑指 Offer 53 - I. 在排序数组中查找数字 I
Introduction to tools in TF-A
Codeforces Round #732 (Div. 2) D. AquaMoon and Chess
Yolov5 adds attention mechanism
Gbase database helps the development of digital finance in the Bay Area
Csp-j-2020-excellent split multiple solutions
网络工程师考核的一些常见的问题:WLAN、BGP、交换机
Haut OJ 1357: lunch question (I) -- high precision multiplication
Talking about JVM (frequent interview)