Getting Started with Azure Machine Learning

Machine learning helps predict the weather, route you around traffic jams, and display personalized ads on your web pages. In this course, you will learn how to use Azure machine learning in order to create, deploy, and maintain predictive solutions.
Course info
Rating
(128)
Level
Beginner
Updated
Nov 2, 2016
Duration
2h 14m
Table of contents
Description
Course info
Rating
(128)
Level
Beginner
Updated
Nov 2, 2016
Duration
2h 14m
Description

Every day you see more and more examples of machine learning in your life. In this course, Getting Started with Azure Machine Learning, you will learn how to develop and deploy predictive solutions using Azure Machine Learning. First, you will see how, with a little dragging and dropping, you can create solutions from scratch. Next, if you already have a solution implemented in R or Python, you will learn how to scale them up with Azure Machine Learning. Finally, you'll end the course by learning about how to maintain your Azure Machine Learning solution. After finishing this course, you'll have gone from a machine learning novice to having a prediction solution service ready to integrate into your applications to make them smarter and more useful.

About the author
About the author

Jerry Kurata is a Solutions Architect at InStep Technologies.

More from the author
Deep Learning with Keras
Intermediate
2h 33m
Mar 26, 2018
TensorFlow: Getting Started
Beginner
2h 37m
May 3, 2017
More courses by Jerry Kurata
Section Introduction Transcripts
Section Introduction Transcripts

Course Overview
Hi, my name is Jerry Kurata. Welcome to my course, Getting Started with Azure Machine Learning. We see machine learning predictions being made every day. From helping doctors understand the probability a person has a disease, to determining whether a bank should give a person a loan. You may have wondered how these systems are designed, built, deployed, and maintained. This course will help you unravel that mystery as we use Azure Machine Learning to introduce you to machine learning and the technology behind it. You will see why companies are in such a rush to learn machine learning to grow their business and increase profits. You will learn how we can use Azure and Azure Machine Learning Studio to create machine learning predictive solutions, specifically, you will learn how to gather data, create machine-learning solutions that learn from that data, and evaluate their predictive power. Once we have our solution, we'll deploy it via Azure. This will make our predictive solution available to users as a web service. And to ensure this service continues to provide great performance as data changes, we'll go through the process of maintaining the solution. We will do much of our work with Azure Machine Learning Studio. Azure Machine Learning Studio lets us build much of our machine-learning solution by dragging and dropping modules onto a workspace, but it also lets us incorporate code written in R and Python into our solution. By the end of this course, you'll know how to create, deploy, and maintain machine-learning solutions in Azure and make their predictive capabilities available to users worldwide. I look forward to you joining me in this journey of getting started with Azure Machine Learning from Pluralsight.

Introduction
Hi, I'm Jerry Kurata. Welcome to the Pluralsight course on Getting Started with Azure Machine Learning. In this course you will learn about machine learning and how Microsoft Azure provides a great platform for creating, maintaining, and distributing machine-learning solutions. In this first module, we'll provide some basic information about machine learning in Azure. We will start by getting an understanding of what machine learning is and how it differs from traditional programming. Then we'll go deeper into machine learning and go over the two basic types of machine learning, supervised and unsupervised. We will see each of these types in action, which will clarify how they differ and when each type of machine learning should be used. After that, we will review the machine-learning workflow, which will be our guide to the process of creating a great machine-learning solution. Next, we'll take a look at Azure in general, and then go over specifically how machine learning fits into the rest of Azure. We will end this first module with a summary of what we will cover in the remaining modules of the course. This will be a fun and exciting journey, so let's get started.

Diving Deeper into Azure Machine Learning
In the previous module, we saw how we could use Azure Machine Learning to easily create, run, and evaluate our experiment. But there is so much more that Azure Machine Learning can do. Hi, I'm Jerry Kurata, and welcome back to Getting Started with Azure Machine Learning. In this module of the course, we will increase our understanding of Azure Machine Learning, by diving deeper into Azure Machine Learning Studio. We will get started by taking a look at getting data into Azure Machine Learning. Then we will do advanced data exploration and pre-processing, to ensure we trained our models with the best possible data. Since different algorithms are used based on the data and result we want, we will go through the process of selecting the appropriate algorithm from the dozens that Azure Machine Learning provides. And along the way, we will see how to incorporate R and Python Code into our experiments. To do all this, we're going to create a new experiment that predicts if a person should or should not be given a loan.

Deploying Your Azure ML Solution
Hi, I'm Jerry Kurata and welcome back to Getting Started with Azure Machine Learning. In the previous modules we went through the machine learning work steps of creating and evaluating our trained, predictive model. Now that we have that model, we want to make its predictive capabilities available to others. We will do this by creating a web service interface through which parameters can be passed in and the resulting prediction based on those parameters passed back to the caller. The caller could then incorporate these results into their application. To see how the web service is used, we'll go through some examples of how interactive clients and Azure batch processes can use our predictive model to evaluate credit risk. Sounds like fun so let's get started making our predictive model available to the world.