About this Course
175,336 recent views

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Approx. 24 hours to complete

Suggested: 6 weeks of study, 5-8 hours/week...


Subtitles: English, Korean, Vietnamese, Chinese (Simplified)

Skills you will gain

Python ProgrammingMachine Learning ConceptsMachine LearningDeep Learning

100% online

Start instantly and learn at your own schedule.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Approx. 24 hours to complete

Suggested: 6 weeks of study, 5-8 hours/week...


Subtitles: English, Korean, Vietnamese, Chinese (Simplified)

Syllabus - What you will learn from this course

2 hours to complete


Machine learning is everywhere, but is often operating behind the scenes. <p>This introduction to the specialization provides you with insights into the power of machine learning, and the multitude of intelligent applications you personally will be able to develop and deploy upon completion.</p>We also discuss who we are, how we got here, and our view of the future of intelligent applications.

18 videos (Total 84 min), 6 readings
18 videos
Who we are5m
Machine learning is changing the world3m
Why a case study approach?7m
Specialization overview6m
How we got into ML3m
Who is this specialization for?4m
What you'll be able to do57s
The capstone and an example intelligent application6m
The future of intelligent applications2m
Starting an IPython Notebook5m
Creating variables in Python7m
Conditional statements and loops in Python8m
Creating functions and lambdas in Python3m
Starting GraphLab Create & loading an SFrame4m
Canvas for data visualization4m
Interacting with columns of an SFrame4m
Using .apply() for data transformation5m
6 readings
Important Update regarding the Machine Learning Specialization10m
Slides presented in this module10m
Reading: Getting started with Python, IPython Notebook & GraphLab Create10m
Reading: where should my files go?10m
Download the IPython Notebook used in this lesson to follow along10m
Download the IPython Notebook used in this lesson to follow along10m
2 hours to complete

Regression: Predicting House Prices

This week you will build your first intelligent application that makes predictions from data.<p>We will explore this idea within the context of our first case study, predicting house prices, where you will create models that predict a continuous value (price) from input features (square footage, number of bedrooms and bathrooms,...). <p>This is just one of the many places where regression can be applied.Other applications range from predicting health outcomes in medicine, stock prices in finance, and power usage in high-performance computing, to analyzing which regulators are important for gene expression.</p>You will also examine how to analyze the performance of your predictive model and implement regression in practice using an iPython notebook.

19 videos (Total 82 min), 3 readings, 2 quizzes
19 videos
What is the goal and how might you naively address it?3m
Linear Regression: A Model-Based Approach5m
Adding higher order effects4m
Evaluating overfitting via training/test split6m
Training/test curves4m
Adding other features2m
Other regression examples3m
Regression ML block diagram5m
Loading & exploring house sale data7m
Splitting the data into training and test sets2m
Learning a simple regression model to predict house prices from house size3m
Evaluating error (RMSE) of the simple model2m
Visualizing predictions of simple model with Matplotlib4m
Inspecting the model coefficients learned1m
Exploring other features of the data6m
Learning a model to predict house prices from more features3m
Applying learned models to predict price of an average house5m
Applying learned models to predict price of two fancy houses7m
3 readings
Slides presented in this module10m
Download the IPython Notebook used in this lesson to follow along10m
Reading: Predicting house prices assignment10m
2 practice exercises
Predicting house prices6m
2 hours to complete

Classification: Analyzing Sentiment

How do you guess whether a person felt positively or negatively about an experience, just from a short review they wrote?<p>In our second case study, analyzing sentiment, you will create models that predict a class (positive/negative sentiment) from input features (text of the reviews, user profile information,...).This task is an example of classification, one of the most widely used areas of machine learning, with a broad array of applications, including ad targeting, spam detection, medical diagnosis and image classification.</p>You will analyze the accuracy of your classifier, implement an actual classifier in an iPython notebook, and take a first stab at a core piece of the intelligent application you will build and deploy in your capstone.

19 videos (Total 75 min), 3 readings, 2 quizzes
19 videos
What is an intelligent restaurant review system?4m
Examples of classification tasks4m
Linear classifiers5m
Decision boundaries3m
Training and evaluating a classifier4m
What's a good accuracy?3m
False positives, false negatives, and confusion matrices6m
Learning curves5m
Class probabilities1m
Classification ML block diagram3m
Loading & exploring product review data2m
Creating the word count vector2m
Exploring the most popular product4m
Defining which reviews have positive or negative sentiment4m
Training a sentiment classifier3m
Evaluating a classifier & the ROC curve4m
Applying model to find most positive & negative reviews for a product4m
Exploring the most positive & negative aspects of a product4m
3 readings
Slides presented in this module10m
Download the IPython Notebook used in this lesson to follow along10m
Reading: Analyzing product sentiment assignment10m
2 practice exercises
Analyzing product sentiment22m
2 hours to complete

Clustering and Similarity: Retrieving Documents

A reader is interested in a specific news article and you want to find a similar articles to recommend. What is the right notion of similarity? How do I automatically search over documents to find the one that is most similar? How do I quantitatively represent the documents in the first place?<p>In this third case study, retrieving documents, you will examine various document representations and an algorithm to retrieve the most similar subset. You will also consider structured representations of the documents that automatically group articles by similarity (e.g., document topic).</p>You will actually build an intelligent document retrieval system for Wikipedia entries in an iPython notebook.

17 videos (Total 76 min), 3 readings, 2 quizzes
17 videos
What is the document retrieval task?1m
Word count representation for measuring similarity6m
Prioritizing important words with tf-idf3m
Calculating tf-idf vectors5m
Retrieving similar documents using nearest neighbor search2m
Clustering documents task overview2m
Clustering documents: An unsupervised learning task4m
k-means: A clustering algorithm3m
Other examples of clustering6m
Clustering and similarity ML block diagram7m
Loading & exploring Wikipedia data5m
Exploring word counts5m
Computing & exploring TF-IDFs7m
Computing distances between Wikipedia articles5m
Building & exploring a nearest neighbors model for Wikipedia articles3m
Examples of document retrieval in action4m
3 readings
Slides presented in this module10m
Download the IPython Notebook used in this lesson to follow along10m
Reading: Retrieving Wikipedia articles assignment10m
2 practice exercises
Clustering and Similarity12m
Retrieving Wikipedia articles18m
2 hours to complete

Recommending Products

Ever wonder how Amazon forms its personalized product recommendations? How Netflix suggests movies to watch? How Pandora selects the next song to stream? How Facebook or LinkedIn finds people you might connect with? Underlying all of these technologies for personalized content is something called collaborative filtering. <p>You will learn how to build such a recommender system using a variety of techniques, and explore their tradeoffs.</p> One method we examine is matrix factorization, which learns features of users and products to form recommendations. In an iPython notebook, you will use these techniques to build a real song recommender system.

19 videos (Total 94 min), 3 readings, 2 quizzes
19 videos
Where we see recommender systems in action7m
Building a recommender system via classification4m
Collaborative filtering: People who bought this also bought...6m
Effect of popular items3m
Normalizing co-occurrence matrices and leveraging purchase histories6m
The matrix completion task5m
Recommendations from known user/item features6m
Predictions in matrix form3m
Discovering hidden structure by matrix factorization7m
Bringing it all together: Featurized matrix factorization3m
A performance metric for recommender systems5m
Optimal recommenders2m
Precision-recall curves7m
Recommender systems ML block diagram4m
Loading and exploring song data5m
Creating & evaluating a popularity-based song recommender5m
Creating & evaluating a personalized song recommender5m
Using precision-recall to compare recommender models4m
3 readings
Slides presented in this module10m
Download the IPython Notebook used in this lesson to follow along10m
Reading: Recommending songs assignment10m
2 practice exercises
Recommender Systems18m
Recommending songs6m
2 hours to complete

Deep Learning: Searching for Images

You’ve probably heard that Deep Learning is making news across the world as one of the most promising techniques in machine learning. Every industry is dedicating resources to unlock the deep learning potential, including for tasks such as image tagging, object recognition, speech recognition, and text analysis.<p>In our final case study, searching for images, you will learn how layers of neural networks provide very descriptive (non-linear) features that provide impressive performance in image classification and retrieval tasks. You will then construct deep features, a transfer learning technique that allows you to use deep learning very easily, even when you have little data to train the model.</p>Using iPhython notebooks, you will build an image classifier and an intelligent image retrieval system with deep learning.

18 videos (Total 74 min), 4 readings, 2 quizzes
18 videos
What is a visual product recommender?3m
Learning very non-linear features with neural networks9m
Application of deep learning to computer vision5m
Deep learning performance3m
Demo of deep learning model on ImageNet data2m
Other examples of deep learning in computer vision1m
Challenges of deep learning2m
Deep Features6m
Deep learning ML block diagram3m
Loading image data3m
Training & evaluating a classifier using raw image pixels6m
Training & evaluating a classifier using deep features8m
Loading image data2m
Creating a nearest neighbors model for image retrieval1m
Querying the nearest neighbors model to retrieve images5m
Querying for the most similar images for car image1m
Displaying other example image retrievals with a Python lambda4m
4 readings
Slides presented in this module10m
Download the IPython Notebook used in this lesson to follow along10m
Download the IPython Notebook used in this lesson to follow along10m
Reading: Deep features for image retrieval assignment10m
2 practice exercises
Deep Learning12m
Deep features for image retrieval14m
1 hour to complete

Closing Remarks

In the conclusion of the course, we will describe the final stage in turning our machine learning tools into a service: deployment.<p>We will also discuss some open challenges that the field of machine learning still faces, and where we think machine learning is heading. We conclude with an overview of what's in store for you in the rest of the specialization, and the amazing intelligent applications that are ahead for us as we evolve machine learning.

7 videos (Total 33 min), 1 reading
7 videos
Deploying an ML service3m
What happens after deployment?7m
Open challenges in ML8m
Where is ML going?6m
What's ahead in the specialization5m
Thank you!1m
1 reading
Slides presented in this module10m
2,056 ReviewsChevron Right


started a new career after completing these courses


got a tangible career benefit from this course

Top reviews from Machine Learning Foundations: A Case Study Approach

By BLOct 17th 2016

Very good overview of ML. The GraphLab api wasn't that bad, and also it was very wise of the instructors to allow the use of other ML packages. Overall i enjoyed it very much and also leaned very much

By DPFeb 15th 2016

With a funny and welcoming look and feel, this course introduces machine learning through a hands-on approach, that enables the student to properly understand what ML is all about. Very nicely done!



Carlos Guestrin

Amazon Professor of Machine Learning
Computer Science and Engineering

Emily Fox

Amazon Professor of Machine Learning

About University of Washington

Founded in 1861, the University of Washington is one of the oldest state-supported institutions of higher education on the West Coast and is one of the preeminent research universities in the world....

About the Machine Learning Specialization

This Specialization from leading researchers at the University of Washington introduces you to the exciting, high-demand field of Machine Learning. Through a series of practical case studies, you will gain applied experience in major areas of Machine Learning including Prediction, Classification, Clustering, and Information Retrieval. You will learn to analyze large and complex datasets, create systems that adapt and improve over time, and build intelligent applications that can make predictions from data....
Machine Learning

Frequently Asked Questions

  • Once you enroll for a Certificate, you’ll have access to all videos, quizzes, and programming assignments (if applicable). Peer review assignments can only be submitted and reviewed once your session has begun. If you choose to explore the course without purchasing, you may not be able to access certain assignments.

  • When you enroll in the course, you get access to all of the courses in the Specialization, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. If you only want to read and view the course content, you can audit the course for free.

More questions? Visit the Learner Help Center.