IL - Azure Machine Learning (ML) for the Business
Instructor-Led Training
2 Days
Onsite or Virtual
Course Overview
This course explores Microsoft Azure’s AzureML service offering for students that are either new to machine learning or new to Azure. The course starts with an introduction to various aspects of building experiments in AzureML and using MLStudio to create cohesive machine learning workflows.

Each topic looks at different aspects of AzureML as well as introduces different concepts in machine learning such as regression, clustering and classification and when to use each. The course moves onto more advanced topics such as how the R language can be used to enrich AzureML as well as being able to define neural networks and lastly how to integrate into more complex data orchestrations involving other services in Azure.

Learning format: 
40% presentation
40% hands-on labs
20% whiteboard design 
  • Students will be taught basic machine learning processes and how different components and tasks of Azure Machine Learning map to each step of the process.
  • Introduce students to data science techniques in Azure will be covered.
  • Understand how to import and manipulate data with Azure Machine Learning Studio.
  • How to evaluate model performance in Azure Machine Learning Studio.
  • Understand the use of key machine learning algorithms in Azure Machine Learning Studio.
  • How to leverage external scripts written in R or Python with Azure Machine Learning Studio.
  • How to operationalize an Azure Machine Learning Studio model for consumption by an application.
  • Basic understanding of cloud fundamentals.
  • Background in data analysis, database administration, data architecture or data science.
MODULE 1: Introduction to Azure Machine Learning
This module will provide students with an introduction to Machine Learning and Data Science. We will discuss the importance of Machine Learning in modern applications. Next, we will introduce Azure Machine Learning Studio. We will also cover the Machine Learning process to help students better understand how Machine Learning projects will progress, understand how to answer the right questions with Machine Learning and how to improve model performance and project success.

MODULE 2:  Connecting to Data 
This module will focus on data sources and their use in Azure Machine Learning Studio. We will cover online and offline data sources as well as internal and external data sources. We will examine all the supported data sources and review the benefits of each. We will also review the data import process in Azure Machine Learning Studio. 

MODULE 3: Data Cleansing
This module will introduce students to manipulating data. We will look at the various manipulation tasks available in Azure Machine Learning Studio. We will talk about "dirty data", what it is, and how to deal with it in Machine Learning. We will look at sampling and splitting data for use in cross-validation and data size reduction. We will also discuss scaling and reducing for data normalization and other tasks. 

MODULE 4: Modeling in Azure Machine Learning
In this module we will look at data modeling in Azure Machine Learning Studio. Throughout the module we will dig deeper into the machine learning process. We will cover some of the more common machine learning algorithms such as decision trees, clustering, linear regression, and classification. We will discuss how and when to use different algorithms and how to interpret and visualize the results. We will also discuss the use of R and Python scripts in Azure Machine Learning Studio.

MODULE 5: Operationalizing Azure Machine Learning Models
In this module we will look at leveraging your machine learning experiments in production. We will cover operationalizing the model, removing unnecessary tasks, modifying inputs and outputs, and publishing your machine learning machine learning experiment. We will also look at connecting to and consuming the model with applications. 

Case Study: Architecting a Big Data and Machine Learning Solution
In this architecture session students will design a big data solution leveraging patterns learned throughout the class. The solution will focus on real-time analytics with Azure Machine Learning. 
Lab: Architecting a Big Data and Machine Learning Solution
In this lab the student will build an end-to-end big data and machine learning solution. This will include model training and evaluation, operationalizing machine learning models and visualizing machine learning.
Dedicated Training
Contact Us Today

Dedicated instructor-led training is designed for group training and is delivered by the experts at Opsgility. Delivery availability is anywhere in the world at your location or using advanced virtual training software.

  • Standard or Customized Curriculum
  • Globally Available for Delivery
  • Holistic Learning Plans are Available
  • Industry Recognized Subject Matter Experts