This course is part of the Machine Learning Specialization

4.6
stars
13,231 ratings

Emily Fox +1 more instructor

371,568 already enrolled

Offered By

Machine Learning SpecializationUniversity of Washington

About this Course

92,455 recent views

Do you have data and wonder what it can tell you?  Do you need a deeper understanding of the core ways in which machine learning can improve your business?  Do you want to be able to converse with specialists about anything from regression and classification to deep learning and recommender systems?
In this course, you will get hands-on experience with machine learning from a series of practical case-studies.  At the end of the first course you will have studied how to predict house prices based on house-level features, analyze sentiment from user reviews, retrieve documents of interest, recommend products, and search for images.  Through hands-on practice with these use cases, you will be able to apply machine learning methods in a wide range of domains.

This first course treats the machine learning method as a black box.  Using this abstraction, you will focus on understanding tasks of interest, matching these tasks to machine learning tools, and assessing the quality of the output. In subsequent courses, you will delve into the components of this black box by examining models and algorithms.  Together, these pieces form the machine learning pipeline, which you will use in developing intelligent applications.

Learning Outcomes:  By the end of this course, you will be able to:
   -Identify potential applications of machine learning in practice.  
   -Describe the core differences in analyses enabled by regression, classification, and clustering.
   -Select the appropriate machine learning task for a potential application.  
   -Apply regression, classification, clustering, retrieval, recommender systems, and deep learning.
   -Represent your data as features to serve as input to machine learning models. 
   -Assess the model quality in terms of relevant error metrics for each task.
   -Utilize a dataset to fit a model to analyze new data.
   -Build an end-to-end application that uses machine learning at its core.  
   -Implement these techniques in Python.

Flexible deadlines

Reset deadlines in accordance to your schedule.

Shareable Certificate

Earn a Certificate upon completion

100% online

Start instantly and learn at your own schedule.

Course 1 of 4 in the

Machine Learning Specialization

Approx. 18 hours to complete

English

Could your company benefit from training employees on in-demand skills?

Try Coursera for Business

Skills you will gain

Python Programming
Machine Learning Concepts
Machine Learning
Deep Learning

Flexible deadlines

Reset deadlines in accordance to your schedule.

Shareable Certificate

Earn a Certificate upon completion

100% online

Start instantly and learn at your own schedule.

Course 1 of 4 in the

Machine Learning Specialization

Approx. 18 hours to complete

English

Could your company benefit from training employees on in-demand skills?

Try Coursera for Business

Instructors

Instructor rating

4.67/5 (1,150 Ratings)

Emily Fox

Amazon Professor of Machine Learning

Statistics

450,578 Learners

6 Courses

Carlos Guestrin

Amazon Professor of Machine Learning

Computer Science and Engineering

450,999 Learners

8 Courses

Offered by

University of Washington

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

Learn more about Coursera for Business

Syllabus - What you will learn from this course

Content Rating93%(55,312 ratings)

Week1

Week 1

3 hours to complete

Welcome

3 hours to complete

18 videos (Total 84 min), 8 readings, 1 quiz

18 videos

Welcome to this course and specialization41sWho we are5mMachine learning is changing the world3mWhy a case study approach?7mSpecialization overview6mHow we got into ML3mWho is this specialization for?4mWhat you'll be able to do57sThe capstone and an example intelligent application6mThe future of intelligent applications2mStarting a Jupyter Notebook5mCreating variables in Python7mConditional statements and loops in Python8mCreating functions and lambdas in Python3mStarting Turi Create & loading an SFrame4mCanvas for data visualization4mInteracting with columns of an SFrame4mUsing .apply() for data transformation5m

8 readings

Important Update regarding the Machine Learning Specialization10mSlides presented in this module10mGetting started with Python, Jupyter Notebook, & Turi Create10mWhere should my files go?10mImportant changes from previous courses10mDownload the Jupyter Notebook used in this lesson to follow along10mDownload the Jupyter Notebook used in this lesson to follow along10mDownload Wiki People Data10m

1 practice exercise

SFrames15m

Week2

Week 2

3 hours to complete

Regression: Predicting House Prices

This week you will build your first intelligent application that makes predictions from data.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,...). 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.You will also examine how to analyze the performance of your predictive model and implement regression in practice using a Jupyter notebook.

3 hours to complete

19 videos (Total 82 min), 3 readings, 2 quizzes

19 videos

Predicting house prices: A case study in regression1mWhat is the goal and how might you naively address it?3mLinear Regression: A Model-Based Approach5mAdding higher order effects4mEvaluating overfitting via training/test split6mTraining/test curves4mAdding other features2mOther regression examples3mRegression ML block diagram5mLoading & exploring house sale data7mSplitting the data into training and test sets2mLearning a simple regression model to predict house prices from house size3mEvaluating error (RMSE) of the simple model2mVisualizing predictions of simple model with Matplotlib4mInspecting the model coefficients learned1mExploring other features of the data6mLearning a model to predict house prices from more features3mApplying learned models to predict price of an average house5mApplying learned models to predict price of two fancy houses7m

3 readings

Slides presented in this module10mDownload the Jupyter Notebook used in this lesson to follow along10mPredicting house prices assignment10m

2 practice exercises

Regression30mPredicting house prices30m

Week3

Week 3

3 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?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.You will analyze the accuracy of your classifier, implement an actual classifier in a Jupyter notebook, and take a first stab at a core piece of the intelligent application you will build and deploy in your capstone.

3 hours to complete

19 videos (Total 75 min), 3 readings, 2 quizzes

19 videos

Analyzing the sentiment of reviews: A case study in classification38sWhat is an intelligent restaurant review system?4mExamples of classification tasks4mLinear classifiers5mDecision boundaries3mTraining and evaluating a classifier4mWhat's a good accuracy?3mFalse positives, false negatives, and confusion matrices6mLearning curves5mClass probabilities1mClassification ML block diagram3mLoading & exploring product review data2mCreating the word count vector2mExploring the most popular product4mDefining which reviews have positive or negative sentiment4mTraining a sentiment classifier3mEvaluating a classifier & the ROC curve4mApplying model to find most positive & negative reviews for a product4mExploring the most positive & negative aspects of a product4m

3 readings

Slides presented in this module10mDownload the Jupyter Notebook used in this lesson to follow along10mAnalyzing product sentiment assignment10m

2 practice exercises

Classification30mAnalyzing product sentiment30m

Week4

Week 4

3 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?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).You will actually build an intelligent document retrieval system for Wikipedia entries in an Jupyter notebook.

3 hours to complete

17 videos (Total 76 min), 3 readings, 2 quizzes

17 videos

Document retrieval: A case study in clustering and measuring similarity35sWhat is the document retrieval task?1mWord count representation for measuring similarity6mPrioritizing important words with tf-idf3mCalculating tf-idf vectors5mRetrieving similar documents using nearest neighbor search2mClustering documents task overview2mClustering documents: An unsupervised learning task4mk-means: A clustering algorithm3mOther examples of clustering6mClustering and similarity ML block diagram7mLoading & exploring Wikipedia data5mExploring word counts5mComputing & exploring TF-IDFs7mComputing distances between Wikipedia articles5mBuilding & exploring a nearest neighbors model for Wikipedia articles3mExamples of document retrieval in action4m

3 readings

Slides presented in this module10mDownload the Jupyter Notebook used in this lesson to follow along10mRetrieving Wikipedia articles assignment10m

2 practice exercises

Clustering and Similarity30mRetrieving Wikipedia articles30m

Week5

Week 5

3 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. You will learn how to build such a recommender system using a variety of techniques, and explore their tradeoffs. One method we examine is matrix factorization, which learns features of users and products to form recommendations. In a Jupyter notebook, you will use these techniques to build a real song recommender system.

3 hours to complete

19 videos (Total 94 min), 3 readings, 2 quizzes

19 videos

Recommender systems overview1mWhere we see recommender systems in action7mBuilding a recommender system via classification4mCollaborative filtering: People who bought this also bought...6mEffect of popular items3mNormalizing co-occurrence matrices and leveraging purchase histories6mThe matrix completion task5mRecommendations from known user/item features6mPredictions in matrix form3mDiscovering hidden structure by matrix factorization7mBringing it all together: Featurized matrix factorization3mA performance metric for recommender systems5mOptimal recommenders2mPrecision-recall curves7mRecommender systems ML block diagram4mLoading and exploring song data5mCreating & evaluating a popularity-based song recommender5mCreating & evaluating a personalized song recommender5mUsing precision-recall to compare recommender models4m

3 readings

Slides presented in this module10mDownload the Jupyter Notebook used in this lesson to follow along10mRecommending songs assignment10m

2 practice exercises

Recommender Systems30mRecommending songs30m

Week6

Week 6

3 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.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.Using iPhython notebooks, you will build an image classifier and an intelligent image retrieval system with deep learning.

3 hours to complete

18 videos (Total 74 min), 4 readings, 2 quizzes

18 videos

Searching for images: A case study in deep learning23sWhat is a visual product recommender?3mLearning very non-linear features with neural networks9mApplication of deep learning to computer vision5mDeep learning performance3mDemo of deep learning model on ImageNet data2mOther examples of deep learning in computer vision1mChallenges of deep learning2mDeep Features6mDeep learning ML block diagram3mLoading image data3mTraining & evaluating a classifier using raw image pixels6mTraining & evaluating a classifier using deep features8mLoading image data2mCreating a nearest neighbors model for image retrieval1mQuerying the nearest neighbors model to retrieve images5mQuerying for the most similar images for car image1mDisplaying other example image retrievals with a Python lambda4m

4 readings

Slides presented in this module10mDownload the Jupyter Notebook used in this lesson to follow along10mDownload the Jupyter Notebook used in this lesson to follow along10mDeep features for image retrieval assignment10m

2 practice exercises

Deep Learning30mDeep features for image retrieval30m

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.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.

1 hour to complete

7 videos (Total 33 min), 1 reading

Reviews

4.6

3165 reviews

5 stars
72.45%
4 stars
20.98%
3 stars
3.73%
2 stars
1.07%
1 star
1.75%

TOP REVIEWS FROM MACHINE LEARNING FOUNDATIONS: A CASE STUDY APPROACH

by RMFeb 2, 2022

I was very disappointed with the exclusion of the final courses and the capstone project. The most interesting part of specialization no longer exists and no plausible justification has been given.

by BLOct 16, 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 HVMay 21, 2016

Good for a introductory course if someone is getting started with machine learning, but as part of an specialization i think is useless (for people who are planning to take all the specialization).

by AMFeb 11, 2018

Very interesting course, many thanks to Emily and Carlos.

The approach in explaining materials was exactly what I was looking for in order to understand both applications and implementation of AI.

View all reviews

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.

Frequently Asked Questions

When will I have access to the lectures and assignments?
Access to lectures and assignments depends on your type of enrollment. If you take a course in audit mode, you will be able to see most course materials for free. To access graded assignments and to earn a Certificate, you will need to purchase the Certificate experience, during or after your audit. If you don't see the audit option:
The course may not offer an audit option. You can try a Free Trial instead, or apply for Financial Aid.
The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.
What will I get if I subscribe to this Specialization?
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.
Is financial aid available?
Yes. In select learning programs, you can apply for financial aid or a scholarship if you can’t afford the enrollment fee. If fin aid or scholarship is available for your learning program selection, you’ll find a link to apply on the description page.

More questions? Visit the Learner Help Center.

Build employee skills, drive business results

Discover Coursera for Business

Machine Learning Foundations: A Case Study Approach

About this Course

Skills you will gain