当前位置:网站首页>Yyds dry goods inventory embedded matrix
Yyds dry goods inventory embedded matrix
2022-07-05 03:04:00 【LolitaAnn】
This article is my note sharing , The content mainly comes from teacher Wu Enda's in-depth learning course . [1]
Embedding matrix
We talked about it earlier word embedding. In this section, let's talk about embedding matrix.
In the process of learning , In fact, I will one hot The pile of vectors of is transformed into a embedding Matrix .
That is to say, what you finally get should be a embedding Matrix , Not every word vector .
Let's continue our previous example , Suppose your dictionary is 1 ten thousand . Now you do word embedding choice 300 Features .
Then what you finally get should be a 300×10000 The matrix of dimensions .
We call this matrix word embedding The big matrix of .
from Embedding matrix Get words in e vector
Method 1
Remember ours one-hot Vector . The length of the vector is the length of the word list . The position of the word in the alphabet in the vector is 1, The rest of the figures are 0.
So I want to get . Of a word word embedding, We just need to put one-hot Multiply our vector by word embedding The matrix of .
So we can get the word in the corresponding position e vector .
Those who have studied linear algebra in the above formula should not be difficult to understand .
Let's take a simple example .
Method 2
Theoretically speaking, the above method is feasible , But it is not so used in practical applications . In practical application, we usually use a function to directly create word word embedding To find , Find the vector of the corresponding position .
In practice, you will never use one 10000 Of length word embedding, Because it's really a little short . So you should be exposed to a very large matrix . If a large matrix is multiplied by a super long one-hot If the vectors of are multiplied , Its computational overhead is very large .
边栏推荐
- Class inheritance in C #
- Character painting, I use characters to draw a Bing Dwen Dwen
- The perfect car for successful people: BMW X7! Superior performance, excellent comfort and safety
- This + closure + scope interview question
- Privatization lightweight continuous integration deployment scheme -- 01 environment configuration (Part 1)
- SFTP cannot connect to the server # yyds dry goods inventory #
- Returns the lowest common ancestor of two nodes in a binary tree
- Kbp206-asemi rectifier bridge kbp206
- How to make OS X read bash_ Profile instead of Profile file - how to make OS X to read bash_ profile not . profile file
- Daily question 2 12
猜你喜欢
Pdf things
The perfect car for successful people: BMW X7! Superior performance, excellent comfort and safety
College Students' innovation project management system
2021 Li Hongyi machine learning (2): pytorch
Apache build web host
LeetCode146. LRU cache
Elfk deployment
this+闭包+作用域 面试题
Pat grade a 1119 pre- and post order traversals (30 points)
【LeetCode】404. Sum of left leaves (2 brushes of wrong questions)
随机推荐
Apache build web host
【LeetCode】98. Verify the binary search tree (2 brushes of wrong questions)
TCP security of network security foundation
Ask, does this ADB MySQL support sqlserver?
2021 Li Hongyi machine learning (3): what if neural network training fails
Port, domain name, protocol.
2021 Li Hongyi machine learning (1): basic concepts
SFTP cannot connect to the server # yyds dry goods inventory #
Scientific research: are women better than men?
Azkaban actual combat
SQL performance optimization skills
Asemi rectifier bridge 2w10 parameters, 2w10 specifications, 2w10 characteristics
el-select,el-option下拉选择框
8. Commodity management - commodity classification
打破信息茧房-我主动获取信息的方法 -#3
Good documentation
Linux安装Redis
Anchor free series network yolox source code line by line explanation Part 2 (a total of 10, ensure to explain line by line, after reading, you can change the network at will, not just as a participan
腾讯云,实现图片上传
How can we truncate the float64 type to a specific precision- How can we truncate float64 type to a particular precision?