Eight Machine Learning JavaScript Frameworks to Explore

[譯]：8個值得探索的JavaScript機器學習框架

In this post, you will learn about different JavaScript framework for machine learning: DeepLearn.js, PropelJS, ML-JS, ConvNetJS, KerasJS, STDLib, Limdu.js, and Brain.js.

[譯]：在這篇文章中，你將會學習到以下不同的JavaScript機器學習框架：

DeepLearn.js，PropelJS，ML-JS，ConvNetJS，KerasJs，STDLib，Limdu.js以及Brain.js。

JavaScript developers tend to look out for JavaScript frameworks that can be used to train machine learning models based on different machine learning algorithms. The following are some of the machine learning algorithms based on which models can be trained using different JavaScript frameworks listed in this article:

[譯]：JavaScript開發人員傾向于尋找可用于機器學習模型訓練的JavaScript框架。下面是一些機器學習算法，這些算法基于本文中列出的不同JavaScript框架來模型訓練：

• Simple linear regression
• [譯]：簡單線性回歸
  
• Multi-variate linear regression
• [譯]：多變量線性回歸
  
• Logistic regression
• [譯]：邏輯回歸
  
• Naive Bayesian
• [譯]：樸素貝葉斯分類算法
  
• K-nearest neighbor (KNN)
• [譯]：K最鄰近分類算法
  
• K-means
• [譯]：k-means
  
• Support vector machine (SVM)
• [譯]：支持向量機
• Random forest
• [譯]：隨機森林
• Decision tree
• [譯]：決策樹
  
• Feedforward neural network
• [譯]：前饋神經網絡
  
• Deep learning network
• [譯]：深度學習網絡
  

In this post, you will learn about different JavaScript framework for machine learning. They are some of the following:

[譯]：在這篇文章中，你會學到不同的JavaScript機器學習框架，它們如下：

DeepLearn.js

Deeplearn.js is an open-source machine learning JavaScript library by Google, which can be used for different purposes such as training neural networks in the browser, understanding ML models, for education purposes, etc. You can run pre-trained models in inference mode. One can write the code in Typescript (ES6 JavaScript) or ES5 JavaScript. Ypi can get started very quickly by including the following code within a?head tag in the HTML file and writing JS programs for building the model.

[譯]：Deeplearn.js是一個谷歌開源的JavaScript機器學習庫，可用于不同的目的，例如在瀏覽器中訓練神經網絡，理解ML模型，用于教育目的等等。你可以在推理模式中運行預先訓練的模型。可以在Typescript（ES6 JavaScript）或ES5 JavaScript中編寫代碼。你可以通過在HTML文件的head標簽中包含以下代碼并編寫用于構建模型的JS程序快速開始。

<script src="https://cdn.jsdelivr.net/npm/deeplearn@latest"></script> <!-- or --> <script src="https://unpkg.com/deeplearn@latest"></script>

PropelJS

Propel, a JavaScript library, provides a GPU-backed numpy-like infrastructure for scientific computing. It could be used both for NodeJS apps and in the browser. The following is the setup code for the browser:

[譯]：Propel，一個JavaScript庫，為科學計算提供了GPU支持的類似numpy的基礎架構。它可以用于NodeJS應用和瀏覽器。以下是瀏覽器的設置代碼：

<script src="https://unpkg.com/propel@3.1.0"></script>

The following code can be used for a NodeJS app:

[譯]：以下是在NodeJS應用中使用的代碼：

npm install propel import { grad } from "propel";

Here is the documentation for PropelJS (Propel doc). Here is the?GitHub page for Propel.

[譯]：這是PropelJS的文檔，這是PropelJS的GitHub。（需要進入請點擊英文中的鏈接）

ML-JS

ML-JS provides machine learning tools for working with NodeJS and browsers. The ML JS tool can be set up using the following code:

[譯]：ML-JS提供了用于使用NodeJS和瀏覽器的機器學習工具。ML JS工具可以使用以下代碼進行設置：

<script src="https://www.lactame.com/lib/ml/2.2.0/ml.min.js"></script>

The following machine learning algorithms are supported:

[譯]：支持以下機器學習算法：

• Unsupervised learning
  
• ?[譯]：無監督學習
  • Principal component analysis (PCA)
  • [譯]：主成分分析（PCA）
    
  • K-means clustering
  • [譯]：K均值聚類算法
    
• Supervised learning
• [譯]：監督學習
  • Simple linear regression
  • [譯]：簡單線性回歸
    
  • Multi-variate linear regression
  • [譯]：多變量變量線性回歸
    
  • Support vector machines (SVM)
  • [譯]：支持向量機（SVM）
    
  • Naive Bayes
  • [譯]：樸素貝葉斯
    
  • K-Nearest Neighbor (KNN)
  • [譯]：K最近鄰（KNN）
    
  • Partial least squares (PLS)
  • [譯]：偏最小二乘法）（PLS）
    
  • Decision tree: CART
  • [譯]：決策樹
    
  • Random forest
  • [譯]：隨機森林
    
  • Logistic regression
  • [譯]：邏輯回歸
    
• Artificial neural network
• [譯]：人工神經網絡
  
  • Feedforward neural network
  • [譯]：前饋神經網絡
    

ConvNetJS

ConvNetJS?is a JavaScript library for training deep learning models (neural networks) entirely in your browser. This library can also be used in NodeJS app.

[譯]：ConvNetJS是一個JavaScript庫，完全用于在瀏覽器中訓練深度學習模型（神經網絡）。這個庫也可以用于NodeJS應用。

In order to get started, get the minified version of ConvNetJS from the?ConvNetJS minified library. This is a?release page for ConvNetJS.

[譯]：想開始的話，可以從ConNetJS壓縮庫中獲取壓縮版的ConevNetJS。這是ConvNetJS的發布網頁。

<script src="convnet-min.js"></script>

The following are some important pages:

[譯]：以下是一些比較重要的網頁：

• NPM package for ConvNetJS
• [譯]：ConvNetJS NPM包
• Getting started
• [譯]：入門
• Documentation
• [譯]：文檔

KerasJS

With?KerasJS, you can run Keras models in the browser, with GPU support using WebGL. Models can also be run in Node.js, but only in CPU mode. Here is the?GitHub page on Keras. The following is the list of Keras models which can be run in the browser:

[譯]：通過KerasJS，你可以在瀏覽器中運行Keras模型，通過使用WebGL得到GPU知識。模型也可運行在Nodejs，但只能在CPU模型下運行。這是Keras的github網頁。以下是可以在瀏覽器中運行的Keras模型列表。

• Basic convnet for MNIST
• [譯]：MNIST的基本convnet
  
• Convolutional variational autoencoder, trained on MNIST
• [譯]：卷積變分自編碼器，在MNIST上訓練
  
• Auxiliary classifier generative adversarial networks (AC-GAN) on MNIST
• [譯]：MNIST上的輔助分類器生成式對抗網絡（AC-GAN）
  
• 50-layer residual network, trained on ImageNet
• [譯]：50層殘差網絡，在ImageNet上訓練
  
• Inception v3, trained on ImageNet
• [譯]：Inception v3，在ImageNet上訓練
  
• DenseNet-121, trained on ImageNet
• [譯]：DenseNet-121，在ImageNet上訓練
  
• SqueezeNet v1.1, trained on ImageNet
• [譯]：SqueezeNet v1.1，在ImageNet上訓練
  
• Bidirectional LSTM for IMDB sentiment classification
• [譯]：IMDB情緒分類的雙向LSTM
  

STDLib

STDLib?is a JavaScript library which can be used to build advanced statistical models and machine learning libraries. It can also be used for plotting and graphics functionality for data visualization and exploratory data analysis.

[譯]：STDLib是一個JavaScript庫，可用于構建高級統計模型和機器學習庫。它也可以用于數據可視化和探索性的數據分析的繪圖和圖形功能。

The following is a list of libraries in relation to ML:

[譯]：以下是與ML有關的庫列表：

• Linear regression via Stochastic gradient descent (@stdlib/ml/online-sgd-regression)
• [譯]：通過隨機梯度下降進行線性回歸（@ stdlib / ml / online-sgd-regression）
• Binary classification via Stochastic gradient descent (@stdlib/ml/online-binary-classification)
• [譯]：通過隨機梯度下降進行二元分類（@ stdlib / ml / online-binary-classification）
  
• Natural language processing (@stdlib/nlp)
• [譯]：自然語言處理（@ stdlib / nlp）
  

Limdu.js

Limdu.js?is a machine-learning framework for Node.js. It supports some of the following:

[譯]：Limdu.js是Node.js的機器學習框架。它支持以下一些內容：

• Binary classification
• [譯]：二元分類
  
• Multi-label classification
• [譯]：多標簽分類
  
• Feature engineering
• [譯]：特征工程
  
• SVM
• [譯]：支持向量機
  

One can go about installing limdu.js using the following command:

[譯]：可以使用以下命令按照黃limdu.js

npm install limdu

Brain.js

Brain.js?is a set of JavaScript libraries for training neural networks and Naive-Bayesian classifier. The following can be used to setup Brain.js:

[譯]：Brain.js是一套用于訓練神經網絡以及樸素貝葉斯分類器的JavaScript庫。以下代碼可用于安裝Brain.js：

npm install brain.js

One can also include the library in the browser using the following code:

[譯]：也可以通過使用以下代碼在瀏覽器中引入庫

<script src="https://raw.githubusercontent.com/harthur-org/brain.js/master/browser.js"></script>

The following can be used to install the Naive Bayesian classifier:

[譯]：以下代碼可以用于安裝樸素貝葉斯分類器

npm install classifier

In this post, you learned about different JavaScript libraries that can be used for training machine learning models in the browser or the Node.js app. For articles on machine learning, we recommend you check out our?machine learning archives.

[譯]：在這篇文章中，你了解了能在瀏覽器和Node.js應用中訓練機器學習模型的不同JavaScript庫。有關機器學習的文章，建議查看我們的機器學習檔案。

總結

以上是生活随笔為你收集整理的Eight Machine Learning JavaScript Frameworks to Explore的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。