当前位置:网站首页>Neural network and deep learning Chapter 1: introduction reading questions
Neural network and deep learning Chapter 1: introduction reading questions
2022-07-05 04:25:00 【Sleeping Raki】
1. Is neural network equivalent to deep learning ?
Not equivalent , Deep learning can use neural network model , Other models can also be used ( Such as deep belief network )
2. What is the main difference between shallow learning and deep learning ?
An important feature of shallow learning is that it does not involve feature learning , Its features are mainly extracted by manual experience or feature transformation methods , The deep learning model can automatically extract features
3. What is learning ? What is a good expression ? What are the representations ?
In order to improve the accuracy of machine learning system , We need to transform the input information into effective features ( such as word embedding), Or more generally, it's called expressing (Representation). If there is an algorithm that can automatically learn effective features , And improve the performance of the final machine learning model , Then this kind of learning can be called representation learning
The key to representation learning is to solve the semantic gap (Semantic Gap) problem . Semantic gap refers to the inconsistency and difference between the underlying characteristics of input data and high-level semantic information . for instance , Computers cannot understand texts directly , The representation of text is only a low-level code in the computer ( Such as ASCII code ), So we need some conversion methods to make the computer “ understand ” semantics .
(1) A good presentation should have strong presentation ability , That is, vectors of the same size can represent more information .
(2) A good presentation should make the follow-up learning task simple , That is, it needs to contain higher-level semantic information .
(3) A good representation should be general , It's task or domain independent . Although the current large
Part of it means that the learning method is still based on a certain task , But we expect that the representations they learned can be easily migrated to other tasks . In machine learning , We often use two ways to express features : Part means (Local Representation) And distributed presentation (Distributed Representation).
Part means : Such as one-hot code
Distributed representation : Such as RGB Show color ,word embedding
4. What is deep learning ?
“ depth ” It refers to the number of nonlinear transformations of the original data ( The layer number ), Deep learning is a sub problem of machine learning , Its main purpose is to learn effective feature representation from data automatically , The key problem to be solved in deep learning is : Contribution distribution problem , That is, the contribution or influence of different components or their parameters in a system to the final system output
边栏推荐
- Convert Boolean to integer value PHP - Convert Boolean to integer value PHP
- 行为感知系统
- 函数(基本:参数,返回值)
- Aperçu en direct | Services de conteneurs ACK flexible Prediction Best Practices
- Moco is not suitable for target detection? MsrA proposes object level comparative learning target detection pre training method SOCO! Performance SOTA! (NeurIPS 2021)...
- Uncover the seven quirky brain circuits necessary for technology leaders
- 线上故障突突突?如何紧急诊断、排查与恢复
- 机器学习 --- 神经网络
- Hexadecimal to decimal
- Hypothesis testing -- learning notes of Chapter 8 of probability theory and mathematical statistics
猜你喜欢
假设检验——《概率论与数理统计》第八章学习笔记
【虚幻引擎UE】实现测绘三脚架展开动画制作
Uncover the seven quirky brain circuits necessary for technology leaders
【虛幻引擎UE】實現UE5像素流部署僅需六步操作少走彎路!(4.26和4.27原理類似)
The scale of computing power in China ranks second in the world: computing is leaping forward in Intelligent Computing
Managed service network: application architecture evolution in the cloud native Era
Longyuan war "epidemic" 2021 network security competition web easyjaba
Power management bus (pmbus)
Function (basic: parameter, return value)
如何优雅的获取每个分组的前几条数据
随机推荐
Is there a sudden failure on the line? How to make emergency diagnosis, troubleshooting and recovery
Serpentine matrix
[moteur illusoire UE] il ne faut que six étapes pour réaliser le déploiement du flux de pixels ue5 et éviter les détours! (4.26 et 4.27 principes similaires)
C26451: arithmetic overflow: use the operator * on a 4-byte value, and then convert the result to an 8-byte value. To avoid overflow, cast the value to wide type before calling the operator * (io.2)
Function (error prone)
【虚幻引擎UE】运行和启动的区别,常见问题分析
[phantom engine UE] only six steps are needed to realize the deployment of ue5 pixel stream and avoid detours! (the principles of 4.26 and 4.27 are similar)
Longyuan war "epidemic" 2021 network security competition web easyjaba
蛇形矩阵
程序员应该怎么学数学
小程序中实现文章的关注功能
Rust blockchain development - signature encryption and private key public key
Learning MVVM notes (1)
About the prompt loading after appscan is opened: guilogic, it keeps loading and gets stuck. My personal solution. (it may be the first solution available in the whole network at present)
Study notes 7
【虚幻引擎UE】打包报错出现!FindPin错误的解决办法
[popular science] basic knowledge of thermal design: heat dissipation analysis of 5g optical devices
基于TCP的移动端IM即时通讯开发仍然需要心跳保活
[phantom engine UE] package error appears! Solutions to findpin errors
【虚幻引擎UE】实现测绘三脚架展开动画制作