Opinto-opas

Objective

Azure Machine Learning (ML) is Microsoft’s cloud-based service for machine learning implementations, which runs on top of Microsoft Azure cloud and allows for building, deploying, tracking machine learning and deep learning models with lots of capabilities and customizations. This course introduces the primary machine learning tools available on the Azure ML studio and focuses on standardized approaches to data analytics and machine learning implementation (e.g., predictive modeling) based on them. By the end of this course, the student will learn to build, train, deploy, automate, manage, and track enterprise-grade machine learning models from scratch in a simplified way using powerful Azure workspaces.

Content

1. Introduction:
Basics of Machine Learning – Importance of Data – Types of Machine Learning – Machine Learning Pipeline – Machine Learning Implementation – Why Cloud-based Services? – Microsoft Azure Cloud Services

2. Azure Machine Learning:
What is Azure ML? – Getting Started with Azure ML – What is Azure ML Studio? – Azure ML Architecture and Concepts – Compute Targets

3. Azure Machine Learning Designer–Working with Data:
Introduction to Azure ML Designer – Create a New Pipeline – Import Data: Manual Data Entry and Sample Datasets – Import Data: Create a Dataset – Visualize the Data – Prepare Data: Select Columns – Prepare Data: Clean Missing Data – Prepare Data: Apply Math Operations – Prepare Data: Split Data

4. Azure Machine Learning Designer–Training and Deployment:
Add Training Modules – Add Evaluation Modules – Set the Default Compute Target – Submit the Pipeline – View Evaluation Results – Create a Real-time Inference Pipeline – Create an Inferencing Cluster – Deploy the Real-time Endpoint – Test the Real-time Endpoint – Clean-up Resources – Algorithm Cheat Sheet for Azure ML Designer

5. Automated Machine Learning:
Introduction to Automated ML – Getting Started with Automated ML – Create and Load a Dataset – Configure Experiment Run – Explore Models – Deploy the Best Model – Prevent Overfitting with Automated ML – Example: Time-Series Forecasting Model

5. Azure Machine Learning Python SDK:
Getting Started with Azure ML in Jupyter Notebooks – Create, Run, and Manage Notebooks – Azure ML Python SDK – Setup Local Computer – Train a Model – Prepare Your Code for Production – Deploy the Model – Automated ML with Python SDK

6. Azure Event Grid:
What is Event Grid? – Event Model and Types – Create Event-driven Workflows – Example 1: Send Email Alerts – Example 2: Data Drift Triggers Retraining

7. What’s More?
Connect to Azure Storage Services – Git Integration for Azure ML – Plan and Manage Costs for Azure ML – Next Steps

Location and time

Course is 100% online (Self-Study) course and study environment is TechClass portal.

Materials

Lecture slides, tutorial videos, quizzes, exercises, project

Teaching methods

This course is 100% virtual thanks to the comprehensive tutorial videos and content prepared for this course.

The student will pass this course after submitting required quiz, assignments, and the final project

Employer connections

N/A

Exam schedules

Online.

International connections

N/A

Completion alternatives

N/A

Student workload

Lectures = 40h
Exercises = 20h
Self-study = 40h
Quizzes = 5h
Project = 35h
Total = 140 hours

Evaluation scale

Hyväksytty/Hylätty

Assessment criteria, satisfactory (1)

- The student is familiar with the cloud-based service.
- The student is familiar with about Azure Machine Learning Studio.
- The student knows about how to use Azure Machine Learning Designer service.
- The student is familiar how to train a model using Azure Machine Learning Designer.
- The student is familiar with concept of Automated Machine Learning service in AML.
- The student is familiar with different compute resource in AML.

Assessment criteria, good (3)

- The student knows how to use Automated Machine Learning Service to implement and deploy different machine learning models.
- The student knows the how to use Jupyter notebook and run and manage it.
- The student is familiar with different assets in Azure Machine Learning Studio.
- The student is familiar with Azure Machine Learning SDK.
- The student knows how to setup his/her local computer.
- The student knows how to use Azure machine learning compute resource to train his/her models.
- The student is familiar with the concept of Experiment.
- The student is familiar with the concept of Event Grid.

Assessment criteria, excellent (5)

- The student knows how to create an environment for his/her model.
- The student can prepare his/her code for deploying different machine learning models.
- The student can understand the technical document of Azure Machine learning Services.
- The student is familiar with Microsoft cognitive service.
- The student knows how transfer learning models work.

Assessment methods and criteria

Exercises 50%
Quizzes 25%
Project 25%

Further information

Course is for Diploma in Machine & Deep Learning Students.