About this Course

730,596 recent views

Learner Career Outcomes

32%

started a new career after completing these courses

30%

got a tangible career benefit from this course
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Flexible deadlines
Reset deadlines in accordance to your schedule.
Approx. 18 hours to complete
English

Skills you will gain

Python ProgrammingMachine Learning ConceptsMachine LearningDeep Learning

Learner Career Outcomes

32%

started a new career after completing these courses

30%

got a tangible career benefit from this course
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Flexible deadlines
Reset deadlines in accordance to your schedule.
Approx. 18 hours to complete
English

Offered by

Placeholder

University of Washington

Syllabus - What you will learn from this course

Content RatingThumbs Up93%(49,625 ratings)Info
Week
1

Week 1

3 hours to complete

Welcome

3 hours to complete
18 videos (Total 84 min), 8 readings, 1 quiz
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 a Jupyter Notebook5m
Creating variables in Python7m
Conditional statements and loops in Python8m
Creating functions and lambdas in Python3m
Starting Turi Create & loading an SFrame4m
Canvas for data visualization4m
Interacting with columns of an SFrame4m
Using .apply() for data transformation5m
8 readings
Important Update regarding the Machine Learning Specialization10m
Slides presented in this module10m
Getting started with Python, Jupyter Notebook, & Turi Create10m
Where should my files go?10m
Important changes from previous courses10m
Download the Jupyter Notebook used in this lesson to follow along10m
Download the Jupyter Notebook used in this lesson to follow along10m
Download Wiki People Data10m
1 practice exercise
SFrames15m
Week
2

Week 2

3 hours to complete

Regression: Predicting House Prices

3 hours to complete
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 Jupyter Notebook used in this lesson to follow along10m
Predicting house prices assignment10m
2 practice exercises
Regression30m
Predicting house prices30m
Week
3

Week 3

3 hours to complete

Classification: Analyzing Sentiment

3 hours to complete
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 Jupyter Notebook used in this lesson to follow along10m
Analyzing product sentiment assignment10m
2 practice exercises
Classification30m
Analyzing product sentiment30m
Week
4

Week 4

3 hours to complete

Clustering and Similarity: Retrieving Documents

3 hours to complete
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 Jupyter Notebook used in this lesson to follow along10m
Retrieving Wikipedia articles assignment10m
2 practice exercises
Clustering and Similarity30m
Retrieving Wikipedia articles30m

Reviews

TOP REVIEWS FROM MACHINE LEARNING FOUNDATIONS: A CASE STUDY APPROACH

View all reviews

About the Machine Learning Specialization

Machine Learning

Frequently Asked Questions

More questions? Visit the Learner Help Center.