当前位置:网站首页>Deep learning - Super parameter setting
Deep learning - Super parameter setting
2022-04-23 15:18:00 【Please call me Lei Feng】
One . Over fitting
1. Definition : Given a hypothetical space H, A hypothesis h Belong to H, If there are other assumptions h’ Belong to H, So in the training example h The error rate of h’ Small , But in the whole instance distribution h’ Than h Low error rate , So let's say suppose h Overfitting training data .
2. Popular explanation
3. Common causes
It is mainly over learning and unbalanced sample characteristics , If the segment , It can also include ( Not all the reasons ):
(1) Wrong modeling sample selection , Sample label error, etc , Causes the selected sample data to be insufficient to represent the intended classification rule
(2) Excessive sample noise interference , Make the machine learn the noise , Also considered a feature , Thus disturbing the preset classification rules
(3) The hypothetical model cannot reasonably exist , Or the conditions under which the hypothesis is true are not true (4) Too many parameters , Excessive model complexity
(5) about tree-based Model , If we compare its depth with split There are no reasonable restrictions , It is possible to make the node contain only simple event data (event) Or non-event data (no event), Make it a perfect match though ( fitting ) Training data , But it can't adapt to other data sets
(6) For the neural network model :1). Too many iterations of weight learning (Overtraining),2).BP The algorithm may make the weight converge to the decision surface which is too complex .
4. resolvent
-> Model : neural network : Add dropout,batch normalization Tree based model : Limit depth , Add regularization items and set early termination conditions .
-> Data on : Increase the data set and enhance the data set (augmentation).
Two 、 Regularization
Preliminary knowledge ( Gradient descent method ):https://zhuanlan.zhihu.com/p/113714840
1. The purpose of regularization : A weight accumulation term added for the generalization of the model .
版权声明
本文为[Please call me Lei Feng]所创,转载请带上原文链接,感谢
https://yzsam.com/2022/04/202204231508367130.html
边栏推荐
- Kubernetes详解(九)——资源配置清单创建Pod实战
- MySQL sync could not find first log file name in binary log index file error
- What is the role of the full connection layer?
- Redis cluster principle
- 机器学习——逻辑回归
- LeetCode153-寻找旋转排序数组中的最小值-数组-二分查找
- Modify the default listening IP of firebase emulators
- C language super complete learning route (collection allows you to avoid detours)
- Borui data and F5 jointly build the full data chain DNA of financial technology from code to user
- Leetcode149 - maximum number of points on a line - Math - hash table
猜你喜欢
asp. Net method of sending mail using mailmessage
Leetcode167 - sum of two numbers II - double pointer - bisection - array - Search
How to use OCR in 5 minutes
Nuxt project: Global get process Env information
On the day of entry, I cried (mushroom street was laid off and fought for seven months to win the offer)
LeetCode167-两数之和II-双指针-二分-数组-查找
Openfaas practice 4: template operation
About UDP receiving ICMP port unreachable
Have you learned the basic operation of circular queue?
Leetcode149 - maximum number of points on a line - Math - hash table
随机推荐
填充每个节点的下一个右侧节点指针 II [经典层次遍历 | 视为链表 ]
Sqlserver transaction and lock problem
Compiling OpenSSL
[thymeleaf] handle null values and use safe operators
How to design a good API interface?
Leetcode151 - invert words in string - String - simulation
Leetcode165 compare version number double pointer string
Comment eolink facilite le télétravail
What exactly does the distributed core principle analysis that fascinates Alibaba P8? I was surprised after reading it
Share 20 tips for ES6 that should not be missed
About UDP receiving ICMP port unreachable
setcontext getcontext makecontext swapcontext
Wechat applet customer service access to send and receive messages
T2 iCloud日历无法同步
Comparaison du menu de l'illustrateur Adobe en chinois et en anglais
UML学习_day2
Ffmpeg installation error: NASM / yasm not found or too old Use --disable-x86asm for a clipped build
中富金石财富班29800效果如何?与专业投资者同行让投资更简单
Detailed explanation of kubernetes (XI) -- label and label selector
The life cycle of key value in redis module programming