当前位置:网站首页>迭代次数的差异与信息熵
迭代次数的差异与信息熵
2022-07-27 10:26:00 【黑榆】
A | 5 | 7 | 2 | 4 | 3 | 9 | 1 | 6 | 8 |
0 | 5402.955 | 7822.01 | 8358.603 | 11983.15 | 12572.23 | 13346.79 | 23558.45 | 25605.5 | 27905.07 |
用神经网络分类A和B,让A是mnist的0,让B为mnist的1-9,将收敛误差固定,统计迭代次数并排序,可以得到形态数轴。排序为
5 7 2 4 3 9 1 6 8
那这组排序是否取决于图片B的信息熵?答案应该否定的,
A | 5 | 7 | 2 | 4 | 3 | 9 | 1 | 6 | 8 |
0 | 5402.955 | 7822.01 | 8358.603 | 11983.15 | 12572.23 | 13346.79 | 23558.45 | 25605.5 | 27905.07 |
7 | 4 | 5 | 6 | 9 | 2 | 8 | 0 | 3 | |
1 | 9568.94 | 9577.513 | 10137.68 | 10241.39 | 10721.14 | 11792.54 | 16861 | 23558.45 | 35671.24 |
5 | 8 | 0 | 6 | 1 | 7 | 9 | 4 | 3 | |
2 | 7100.643 | 7658.015 | 8358.603 | 9360.106 | 11792.54 | 12555.62 | 13772.15 | 19984.86 | 33389.61 |
6 | 5 | 0 | 4 | 8 | 7 | 9 | 2 | 1 | |
3 | 8136.266 | 11703.08 | 12572.23 | 15199.52 | 17015.68 | 17331.39 | 19919.65 | 33389.61 | 35671.24 |
5 | 8 | 7 | 6 | 1 | 0 | 3 | 9 | 2 | |
4 | 5689.266 | 6106.347 | 7572.704 | 9020.96 | 9577.513 | 11983.15 | 15199.52 | 18523.66 | 19984.86 |
6 | 0 | 4 | 8 | 9 | 2 | 7 | 1 | 3 | |
5 | 5362.608 | 5402.955 | 5689.266 | 6116.397 | 6794.688 | 7100.643 | 8617.161 | 10137.68 | 11703.08 |
5 | 3 | 8 | 7 | 4 | 9 | 2 | 1 | 0 | |
6 | 5362.608 | 8136.266 | 8626.678 | 8983.447 | 9020.96 | 9044.211 | 9360.106 | 10241.39 | 25605.5 |
8 | 4 | 0 | 5 | 6 | 1 | 2 | 3 | 9 | |
7 | 7073.432 | 7572.704 | 7822.01 | 8617.161 | 8983.447 | 9568.94 | 12555.62 | 17331.39 | 20211.46 |
4 | 5 | 9 | 7 | 2 | 6 | 1 | 3 | 0 | |
8 | 6106.347 | 6116.397 | 6966.322 | 7073.432 | 7658.015 | 8626.678 | 16861 | 17015.68 | 27905.07 |
5 | 8 | 6 | 1 | 0 | 2 | 4 | 3 | 7 | |
9 | 6794.688 | 6966.322 | 9044.211 | 10721.14 | 13346.79 | 13772.15 | 18523.66 | 19919.65 | 20211.46 |
因为如果分类原点不是0而是其余的形态,则分类对象的排序完全不同。而单张图片的信息熵不可能因为分类原点的改变而改变。所以如何解释迭代次数排序与信息熵无关这个矛盾?
假设1:完全相同的两个对象无法被分成两类,与之对应的分类迭代次数为无穷大。
推论1:相等收敛误差下迭代次数越大表明二者差异越小。
按照迭代次数假设,迭代次数取决于分类原点和分类对象二者之间的差异。这是两个对象之间的相互作用,并不是个体行为。因此是分类原点和分类对象共同决定了迭代次数,而并不完全取决于分类对象,因此分类对象的信息熵与迭代次数差异无关。
单调性,即发生概率越高的事件,其所携带的信息熵越低
或者按照信息熵单调性的定义,比如如果两张图片越相似,单个像素的不确定性越小,对神经网络的输入来说这个形态发生的概率就越高,这两张图片作为一个整体的信息熵就越低。因此迭代次数与分类原点和分类对象作为一个整体的信息熵成反比。

因此迭代次数的倒数是分类对象和分类原点作为一个整体的信息熵的量度。
边栏推荐
- Set up Samba service
- 阿里邮箱web端登录转圈的处理
- 对象数组去重
- Distributed block device replication: client
- 学习笔记-简易服务器实现
- ECCV 2022 | 同时完成四项跟踪任务!Unicorn: 迈向目标跟踪的大统一
- Shardingproxy sub database and table actual combat and comparison of similar products
- 北京公示儿童鞋抽查 8组批产品不合格琪尔特登榜
- Pyqt5 rapid development and practice 4.2 QWidget
- [Flink] Flink builds clusters in standalone mode
猜你喜欢

TDengine 商业生态合作伙伴招募开启

让人深思:句法真的重要吗?邱锡鹏组提出一种基于Aspect的情感分析的强大基线...
[email protected] @Eslint loader / index. JS) "/>Eslint's error message module error (from./node_modules/ [email protected] @Eslint loader / index. JS)

Metaspolit

数据类型与变量

How to build a data index system is the most effective. It will take you a quick start from 0 to 1

Li Kou brush question 02 (sum of three numbers + sum of maximum subsequence + nearest common ancestor of binary tree)

Share machine learning notes (PDF version) + practical projects (dataset + code)
![[Flink] Flink builds clusters in standalone mode](/img/5b/e566fdd2792b5cda7d37d308ee32e2.png)
[Flink] Flink builds clusters in standalone mode

JVM -- Analysis of bytecode
随机推荐
深度解析:什么是Diffusion Model?
Using skills of word
The largest square of leetcode (violence solving and dynamic programming solving)
Customized modification based on jira7.9.2
这种动态规划你见过吗——状态机动态规划之股票问题(上)
Chengying, kangaroo cloud one-stop fully automated operation and maintenance steward, is officially open source
Open source project - taier1.2 release, new workflow, tenant binding simplification and other functions
flask_ Output fields in restful (resources, fields, marshal, marshal_with)
NodeJS中Error: getaddrinfo ENOTFOUND localhost
Establishment of NFS server
Apache cannot start in phpstudy
No Identifier specified for entity的解决办法
GEE中下载过程中出现 Error: Image.clipToBoundsAndScale, argument 'input'
Review and Prospect of encrypted traffic identification based on deep learning
华硕无双,这可能是屏幕最好的平价高刷轻薄笔记本
Google browser screenshot tips
JVM -- Analysis of bytecode
Symmetric encryption and asymmetric encryption
File upload vulnerability bypass method
学习笔记-简易服务器实现