• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    公众号

microsoft/hol-azure-machine-learning: Introduction to Machine Learning and Azure ...

原作者: [db:作者] 来自: 网络 收藏 邀请

开源软件名称(OpenSource Name):

microsoft/hol-azure-machine-learning

开源软件地址(OpenSource Url):

https://github.com/microsoft/hol-azure-machine-learning

开源编程语言(OpenSource Language):

JavaScript 76.7%

开源软件介绍(OpenSource Introduction):

Azure Machine Learning Hands on Labs

This content is designed for audience without any prior Machine learning knowledge. It starts from very basics and goes to advanced topics. We will try to keep this content live and include more and more advanced lab sessions with real life scenarious. Thanks for your support and feedback to make this content better.

Suggested timeline for Azure Machine Learning Hands On Lab (HOL)

Time (min) Activity
50 Introduction to Machine Learning
20 Lab1 - Setting up development environment
45 Lab2 - Introduction to R, Python & Data Synth
45 Lab3 - AzureML Experiments & Data Interaction
60 Lab4 - Develop and Consume AzureML Models
45 Lab5 - Custom Scripts (R & Python) in AML
60 Lab6 - Evaluate model performance in AML
60 Lab7 - Azure ML Batch Score, Retrain, Production and Automatization
45 Lab8 - Recommendation System
45 Lab9 - Monetizing Azure ML Solution
90 Lab10 - Case Study: Optical character recognition

Detailed contents of the HOL

  1. Setting up development environment

    • Overview
      • Objectives
      • Requirements
    • Create free tier Azure ML account
    • Create standard tier Azure ML account
    • Install R and R Studio
    • Install Anaconda Python
  2. Introduction to R, Python & Data Synth

    • Overview
      • Objectives
      • Requirements
    • Generate Synthetic Data
      • Microsoft Excel
      • R
      • Python
      • Microsoft Azure SQL Server
      • Microsoft Azure Blob Storage
    • Other Dataset sources
  3. AzureML Experiments & Data Interaction

    • Overview
      • Objectives
      • Requirements
    • Creating AzureML Experiment
    • Accessing Data
      • Access data, use existing dataset
      • Upload your own dataset
      • Upload your own compressed dataset
      • Manually enter data
      • Access data on Azure Storage
      • Access data on Azure SQL Database
      • Get data from an HTTP web request
  4. Develop and Consume AzureML Models

    • Overview
      • Objectives
      • Requirements
    • Working with AzureML Models
      • Training a model
      • Publishing a trained model as Web Service
      • Removing Web Service Redundant input & output parameters
      • Consume the ML Web Service in a C# application
      • Input data type
  5. Custom Scripts (R & Python) in AML

    • Overview
      • Objectives
      • Requirements
    • R & Python Script Modules
      • Using Execute R Script module
      • Using Python Script module
      • R & Python compatibility with Azure ML
  6. Evaluate model performance in AML

    • Overview
      • Objectives
      • Requirements
    • Performance evaluation
      • Splitting data
      • Scoring the model
      • Evaluate a Regression model
      • Evaluate more than one model
      • Cross Validation
    • Performance evaluation (cont.)
      • Evaluate a Binary classification model
      • Comparing two binary classification model
      • Cross Validation on Binary Classification
      • Evaluating a Multi-class classification model
    • Feature engineering
      • Which feature is or is not important?
      • Simpler method to measure a feature’s importance
  7. Azure ML Batch Score, Retrain, Production and Automatization

    • Overview
      • Objectives
      • Requirements
    • Importance of Retraining, seeing the whole picture
    • Batch and Request/Response scoring web services
      • Stages to create a scoring web service
        • Request/Response Service (RRS)
        • Batch Execution Service (BES)
        • Web Service Input/Output Parameter alternatives
    • Azure ML Retraining
  8. Recommendation System

    • Overview
      • Objectives
      • Requirements
    • Generate synthetic data
    • Recommend items to users
    • Find related users
    • Find related items
    • What to recommend for a brand new user?
  9. Monetizing Azure ML Solution

    • Overview
      • Objectives
      • Requirements
    • Azure ML Web Service Details
    • Create Azure Management API Service
    • CORS issue with Azure Machine Learnin Web Services
    • Restrict or Rate limit your Web Service
    • Test and Publish your Web Service
  10. Case Study: Optical character recognition

    • Overview
      • Objectives
      • Requirements
    • Exploring and Understanding the Dataset
      • Process MINST database in Azure ML with Python script
      • Generate image tiles
    • Azure ML solution for OCR
      • Develope Azure ML experiment
      • Deploy as webservice
      • Parameters needed to publish with management API
    • Consuming the ML solution
      • Security of the API
    • Develop web application
      • Publish as Azure Web Application
    • Test the solution
    • Refine Features, Feature Engineering



鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap