当前位置:网站首页>Neural networks and deep learning Chapter 2: machine learning overview reading questions
Neural networks and deep learning Chapter 2: machine learning overview reading questions
2022-07-05 04:25:00 【Sleeping Raki】
1. What is machine learning ?
informally , machine learning (Machine Learning,ML) That is, let the computer learn from the data automatically , Get some kind of knowledge ( Or law ). As a subject , Machine learning usually refers to a kind of problem and the method to solve it , That is, how to get data from observation ( sample ) Looking for the law in the world , And use the learned rules ( Model ) Predict unknown or unobservable data .
2. Why should each sample in the training set be independent and identically distributed ?
The question of Zhihu : Why in machine learning , Let's assume that our data is independent and identically distributed ?
3. There are three basic elements of machine learning ?
Model , Learning rules , optimization algorithm
4. Why does the model over fit ? What is the method to prevent the model from over fitting ? It's not fitting ?
5. Why use SGD, and mini-batch gradient descent ?
6. Why use Ridge Regression instead of vanilla Linear regression of ?
7. What is the maximum a posteriori estimate ?
8. What is the connection and difference between deviation and variance ?
9. What is supervised learning , What is unsupervised learning , Illustrate with examples ?
10.L1 Why does regularization lead to sparse features ?
11.F1 When to use macro average for scores , When to use micro averaging ?
12. Why use cross validation ?
13. Talk about right no free lunch The understanding of the theorem
14. Talk about the understanding of the principle of Occam razor
15. What is? inductive bias(prior)?
边栏推荐
- level18
- Serpentine matrix
- Longyuan war "epidemic" 2021 network security competition web easyjaba
- Threejs realizes the drawing of the earth, geographical location annotation, longitude and latitude conversion of world coordinates threejs coordinates
- Threejs implements labels and displays labels with custom styles
- 指针函数(基础)
- Threejs realizes rain, snow, overcast, sunny, flame
- How can CIOs use business analysis to build business value?
- MacBook安装postgreSQL+postgis
- Basic analysis of IIC SPI protocol
猜你喜欢
Sword finger offer 04 Search in two-dimensional array
Power management bus (pmbus)
Uncover the seven quirky brain circuits necessary for technology leaders
技术教程:如何利用EasyDSS将直播流推到七牛云?
Network layer - forwarding (IP, ARP, DCHP, ICMP, network layer addressing, network address translation)
如何实现实时音视频聊天功能
Seven join join queries of MySQL
A real day for Beijing programmers!!!!!
[uniapp] system hot update implementation ideas
Threejs realizes the drawing of the earth, geographical location annotation, longitude and latitude conversion of world coordinates threejs coordinates
随机推荐
Introduction to RT thread kernel (4) -- clock management
Seven join join queries of MySQL
[uniapp] system hot update implementation ideas
How can CIOs use business analysis to build business value?
All in one 1413: determine base
机器学习 --- 决策树
SPI read / write flash principle + complete code
Hypothesis testing -- learning notes of Chapter 8 of probability theory and mathematical statistics
web资源部署后navigator获取不到mediaDevices实例的解决方案(navigator.mediaDevices为undefined)
Possible stack order of stack order with length n
Behavior perception system
Observable time series data downsampling practice in Prometheus
Realize the attention function of the article in the applet
This is an age of uncertainty
技术教程:如何利用EasyDSS将直播流推到七牛云?
Kwai, Tiktok, video number, battle content payment
PHP读取ini文件并修改内容写入
取余操作是一个哈希函数
After the deployment of web resources, the navigator cannot obtain the solution of mediadevices instance (navigator.mediadevices is undefined)
【虚幻引擎UE】实现UE5像素流部署仅需六步操作少走弯路!(4.26和4.27原理类似)