This course is designed to introduce you to the machine learning and the data science workflow using the simple yet powerful drag-and-drop interface of Azure Machine Learning Studio.
You will find all the course content in student_resources.
Have you tried to learn about machine learning but ended up spending most of your time writing and debugging your code? Learning about machine learning can often be intimidating because students are expected to know R or Python, or at least learn it as they go. While these programming languages are absolutely essential to anyone seriously contemplating a career in data science, they can sometimes hold us back or derail us when our primary objective is to understand machine learning as a process. R and Python can be used in Azure ML Studio to give us more power and flexibility, but we not will emphasize them beyond providing a few examples.
It allows you to learn how to think like a data scientist, learn about machine learning concepts and best practices without being held back by the complexities of any particular programming language (usually R or Python). While we do cover some programming examples just to familiarize you, no background in programming is needed to take this course. Instead, come prepared to learn concepts and best practices and consolidate them through hands-on exercises in the Azure ML Studio.
There are no pre-requisites for this course other than basic algebra.
After completing this course, you will have a deeper understanding of Machine Learning and how data scientists think and talk about building ML solutions. We will introduce you to some of the most fundamental machine learning algorithms, such as linear regression and decision trees. However, this course is not about learning specific ML algorithms and the ones we introduce are just to help build a good intuition around them. Instead, we focus our attention on the practice of machine learning and cover concepts such as
- What is the data science process life cycle?
- What are the different types of ML algorithms (or models)?
- How do we train, test and evaluate a model?
- How do we choose one model versus another?
- What do we mean by model deployment or operationalization?
Labs are a big part of this course and we recommend that you take them seriously and take the time to work on them. Even if your ultimate goal is not to build ML models in person, the labs will really solidify your knowledge and understanding of the concepts we cover in the course.
This course is very lab-heavy and the exercises are meant to reinforce what is learned during the course as well as occasionally introduce new ideas. We highly recommend that you spend the recommended time on each lab. Access to Azure ML Studio at https://studio.azureml.net is all that is needed for the labs. To have access, participants either need an Azure account or need to request a guest account. Please go to the website for more instructions.
The audience for this course can be anyone as there are no pre-requisites, but here are some scenarios to consider:
- You are a data scientist and want to know how to leverage the Azure ML Studio in your work.
- You are an aspiring data scientist who needs to learn the fundamentals of machine learning without being bogged down by specifics of languages like R or Python.
- You are a solutions architect and need to have a more solid understanding of the data science process.
- You are a developper, architect, or sales engineer and need to have a fundamental understanding of data science which would allow you to interface with data scientists and speak their language.
Please let us know how we can improve our content.
Created by a Microsoft Employee.