Introduction to Applied Machine Learning

Introduction to Applied Machine Learning

This course is part of Machine Learning: Algorithms in the Real World Specialization

Instructor: Anna Koop

Access provided by L'Oréal

27,765 already enrolled

4 modules

Gain insight into a topic and learn the fundamentals.

747 reviews

Intermediate level

Some related experience required

Flexible schedule

7 hours to complete

Learn at your own pace

98%

Most learners liked this course

4 modules

Gain insight into a topic and learn the fundamentals.

747 reviews

Intermediate level

Some related experience required

Flexible schedule

7 hours to complete

Learn at your own pace

98%

Most learners liked this course

Skills you'll gain

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

5 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the Machine Learning: Algorithms in the Real World Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 4 modules in this course

This course is for professionals who have heard the buzz around machine learning and want to apply machine learning to data analysis and automation. Whether finance, medicine, engineering, business or other domains, this course will introduce you to problem definition and data preparation in a machine learning project.

By the end of the course, you will be able to clearly define a machine learning problem using two approaches. You will learn to survey available data resources and identify potential ML applications. You will learn to take a business need and turn it into a machine learning application. You will prepare data for effective machine learning applications. This is the first course of the Applied Machine Learning Specialization brought to you by Coursera and the Alberta Machine Intelligence Institute.

This week, you will learn about what machine learning (ML) actually is, contrast different problem scenarios, and explore some common misconceptions about ML. You will apply this knowledge by identifying different components essential to a machine learning business solution.

What's included

12 videos6 readings2 assignments3 discussion prompts

12 videosTotal 44 minutes

Introduction to the Applied Machine Learning Specialization3 minutes
Instructor Introduction1 minute
Introduction to Course 12 minutes
What is Artificial Intelligence and Machine Learning?5 minutes
What about Data Science?4 minutes
The Machine Learning Process5 minutes
The Three Kinds of Machine Learning3 minutes
Classification: What is it and how does it work?4 minutes
Regression: Fitting lines and predicting numbers4 minutes
Unsupervised Learning4 minutes
Reinforcement Learning6 minutes
Weekly Summary2 minutes

6 readingsTotal 60 minutes

What about Deep Learning? (supplemental)10 minutes
Fooling Neural Networks (supplemental)10 minutes
How to Curate A Ground Truth For Your Business Dataset (Required)10 minutes
Learning From Multiple Annotators: A Survey (supplemental)10 minutes
Inferring the Ground Truth Through Crowdsourcing (supplemental)10 minutes
Semi Supervised Learning (required)10 minutes

2 assignmentsTotal 30 minutes

Concepts and Definitions20 minutes
Identifying Machine Learning Techniques10 minutes

3 discussion promptsTotal 30 minutes

Artificial Intelligence Viewpoints10 minutes
Meet and Greet!10 minutes
Misunderstandings surrounding AI and ML10 minutes

This week, you will learn how to translate a business need into a machine learning problem. We'll walk through some applied examples so you can get a feel for what makes a well-defined question for your QuAM. Narrowing down your question and making sure you have the data necessary to learn is critical to ML success!

What's included

8 videos4 readings1 assignment2 discussion prompts

8 videosTotal 34 minutes

Generalization and how machines actually learn6 minutes
Features and transformations of raw data6 minutes
Farmer Betty and Her Precision Agriculture Plans4 minutes
What to consider when using your QuAM3 minutes
Broad Examples Narrowed Down5 minutes
Identify Business Evaluation4 minutes
Everything is a Proxy4 minutes
Weekly Summary2 minutes

4 readingsTotal 40 minutes

A Brief Introduction into Precision Agriculture10 minutes
Farmer Betty Tried Unsupervised Learning (required)10 minutes
Data is Central to Your ML Problem (required)10 minutes
Martin Zinkevich's Rules for ML (supplemental)10 minutes

1 assignment

Machine Learning in the Real World Review0 minutes

2 discussion promptsTotal 20 minutes

Explainability and Accuracy for a QuAM10 minutes
All About Proxies10 minutes

This week is all about data. You will learn about data acquisition and understand the various sources of training data. We'll talk about how much data you need and what pitfalls might arise, including ethical issues.

What's included

9 videos2 readings1 assignment2 discussion prompts

9 videosTotal 34 minutes

Sources of Training Data3 minutes
How Much Data Do I Need?4 minutes
Ethical Issues4 minutes
Bias in Data Sources3 minutes
Noise and Sources of Randomness5 minutes
Image Classification Example3 minutes
Data Cleaning: Everybody's favourite task5 minutes
Why you need to set up a Data Pipeline5 minutes
Weekly Summary2 minutes

2 readingsTotal 20 minutes

Data Protection Laws (required)10 minutes
Government readings on data privacy (supplemental)10 minutes

1 assignment

Understanding Data for ML0 minutes

2 discussion promptsTotal 20 minutes

Sources of Data10 minutes
Bias and Noise10 minutes

This week you will learn about the Machine Learning Process Lifecycle (MLPL). After understanding the definitions and components of the MLPL you will analyze the application of the MLPL on a case study.