Stanford University

About this Course

Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you'll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you'll learn about some of Silicon Valley's best practices in innovation as it pertains to machine learning and AI.
This course provides a broad introduction to machine learning, datamining, and statistical pattern recognition. Topics include: (i) Supervised learning (parametric/non-parametric algorithms, support vector machines, kernels, neural networks). (ii) Unsupervised learning (clustering, dimensionality reduction, recommender systems, deep learning). (iii) Best practices in machine learning (bias/variance theory; innovation process in machine learning and AI). The course will also draw from numerous case studies and applications, so that you'll also learn how to apply learning algorithms to building smart robots (perception, control), text understanding (web search, anti-spam), computer vision, medical informatics, audio, database mining, and other areas.

Start instantly and learn at your own schedule.

Suggested: 7 hours/week

Subtitles: English, Spanish, Hindi, Japanese, Chinese (Simplified)

Machine LearningArtificial Neural NetworkLogistic RegressionLinear Regression

Start instantly and learn at your own schedule.

Suggested: 7 hours/week

Subtitles: English, Spanish, Hindi, Japanese, Chinese (Simplified)

Section

Welcome to Machine Learning! In this module, we introduce the core idea of teaching a computer to learn concepts using data—without being explicitly programmed. The Course Wiki is under construction. Please visit the resources tab for the most complete and up-to-date information....

5 videos (Total 42 min), 9 readings, 1 quiz

Welcome6m

What is Machine Learning?7m

Supervised Learning12m

Unsupervised Learning14m

Machine Learning Honor Code8m

What is Machine Learning?5m

How to Use Discussion Forums4m

Supervised Learning4m

Unsupervised Learning3m

Who are Mentors?3m

Get to Know Your Classmates8m

Frequently Asked Questions11m

Lecture Slides20m

Introduction10m

Linear regression predicts a real-valued output based on an input value. We discuss the application of linear regression to housing price prediction, present the notion of a cost function, and introduce the gradient descent method for learning....

7 videos (Total 70 min), 8 readings, 1 quiz

Cost Function8m

Cost Function - Intuition I11m

Cost Function - Intuition II8m

Gradient Descent11m

Gradient Descent Intuition11m

Gradient Descent For Linear Regression10m

Model Representation3m

Cost Function3m

Cost Function - Intuition I4m

Cost Function - Intuition II3m

Gradient Descent3m

Gradient Descent Intuition3m

Gradient Descent For Linear Regression6m

Lecture Slides20m

Linear Regression with One Variable10m

This optional module provides a refresher on linear algebra concepts. Basic understanding of linear algebra is necessary for the rest of the course, especially as we begin to cover models with multiple variables....

6 videos (Total 61 min), 7 readings, 1 quiz

Addition and Scalar Multiplication6m

Matrix Vector Multiplication13m

Matrix Matrix Multiplication11m

Matrix Multiplication Properties9m

Inverse and Transpose11m

Matrices and Vectors2m

Addition and Scalar Multiplication3m

Matrix Vector Multiplication2m

Matrix Matrix Multiplication2m

Matrix Multiplication Properties2m

Inverse and Transpose3m

Lecture Slides10m

Linear Algebra10m

Section

What if your input has more than one value? In this module, we show how linear regression can be extended to accommodate multiple input features. We also discuss best practices for implementing linear regression....

8 videos (Total 65 min), 16 readings, 1 quiz

Gradient Descent for Multiple Variables5m

Gradient Descent in Practice I - Feature Scaling8m

Gradient Descent in Practice II - Learning Rate8m

Features and Polynomial Regression7m

Normal Equation16m

Normal Equation Noninvertibility5m

Working on and Submitting Programming Assignments3m

Setting Up Your Programming Assignment Environment8m

Accessing MATLAB Online and Uploading the Exercise Files3m

Installing Octave on Windows3m

Installing Octave on Mac OS X (10.10 Yosemite and 10.9 Mavericks and Later)10m

Installing Octave on Mac OS X (10.8 Mountain Lion and Earlier)3m

Installing Octave on GNU/Linux7m

More Octave/MATLAB resources10m

Multiple Features3m

Gradient Descent For Multiple Variables2m

Gradient Descent in Practice I - Feature Scaling3m

Gradient Descent in Practice II - Learning Rate4m

Features and Polynomial Regression3m

Normal Equation3m

Normal Equation Noninvertibility2m

Programming tips from Mentors10m

Lecture Slides20m

Linear Regression with Multiple Variables10m

This course includes programming assignments designed to help you understand how to implement the learning algorithms in practice. To complete the programming assignments, you will need to use Octave or MATLAB. This module introduces Octave/Matlab and shows you how to submit an assignment....

6 videos (Total 80 min), 1 reading, 2 quizzes

Moving Data Around16m

Computing on Data13m

Plotting Data9m

Control Statements: for, while, if statement12m

Vectorization13m

Lecture Slides10m

Octave/Matlab Tutorial10m

Section

Logistic regression is a method for classifying data into discrete outcomes. For example, we might use logistic regression to classify an email as spam or not spam. In this module, we introduce the notion of classification, the cost function for logistic regression, and the application of logistic regression to multi-class classification.
...

7 videos (Total 71 min), 8 readings, 1 quiz

Hypothesis Representation7m

Decision Boundary14m

Cost Function10m

Simplified Cost Function and Gradient Descent10m

Advanced Optimization14m

Multiclass Classification: One-vs-all6m

Classification2m

Hypothesis Representation3m

Decision Boundary3m

Cost Function3m

Simplified Cost Function and Gradient Descent3m

Advanced Optimization3m

Multiclass Classification: One-vs-all3m

Lecture Slides10m

Logistic Regression10m

Machine learning models need to generalize well to new examples that the model has not seen in practice. In this module, we introduce regularization, which helps prevent models from overfitting the training data. ...

4 videos (Total 39 min), 5 readings, 2 quizzes

Cost Function10m

Regularized Linear Regression10m

Regularized Logistic Regression8m

The Problem of Overfitting3m

Cost Function3m

Regularized Linear Regression3m

Regularized Logistic Regression3m

Lecture Slides10m

Regularization10m

Section

Neural networks is a model inspired by how the brain works. It is widely used today in many applications: when your phone interprets and understand your voice commands, it is likely that a neural network is helping to understand your speech; when you cash a check, the machines that automatically read the digits also use neural networks. ...

7 videos (Total 63 min), 6 readings, 2 quizzes

Neurons and the Brain7m

Model Representation I12m

Model Representation II11m

Examples and Intuitions I7m

Examples and Intuitions II10m

Multiclass Classification3m

Model Representation I6m

Model Representation II6m

Examples and Intuitions I2m

Examples and Intuitions II3m

Multiclass Classification3m

Lecture Slides10m

Neural Networks: Representation10m

Section

In this module, we introduce the backpropagation algorithm that is used to help learn parameters for a neural network. At the end of this module, you will be implementing your own neural network for digit recognition.
...

8 videos (Total 78 min), 8 readings, 2 quizzes

Backpropagation Algorithm11m

Backpropagation Intuition12m

Implementation Note: Unrolling Parameters7m

Gradient Checking11m

Random Initialization6m

Putting It Together13m

Autonomous Driving6m

Cost Function4m

Backpropagation Algorithm10m

Backpropagation Intuition4m

Implementation Note: Unrolling Parameters3m

Gradient Checking3m

Random Initialization3m

Putting It Together4m

Lecture Slides10m

Neural Networks: Learning10m

Section

Applying machine learning in practice is not always straightforward. In this module, we share best practices for applying machine learning in practice, and discuss the best ways to evaluate performance of the learned models.
...

7 videos (Total 63 min), 7 readings, 2 quizzes

Evaluating a Hypothesis7m

Model Selection and Train/Validation/Test Sets12m

Diagnosing Bias vs. Variance7m

Regularization and Bias/Variance11m

Learning Curves11m

Deciding What to Do Next Revisited6m

Evaluating a Hypothesis4m

Model Selection and Train/Validation/Test Sets3m

Diagnosing Bias vs. Variance3m

Regularization and Bias/Variance3m

Learning Curves3m

Deciding What to do Next Revisited3m

Lecture Slides10m

Advice for Applying Machine Learning10m

To optimize a machine learning algorithm, you’ll need to first understand where the biggest improvements can be made. In this module, we discuss how to understand the performance of a machine learning system with multiple parts, and also how to deal with skewed data.
...

5 videos (Total 60 min), 3 readings, 1 quiz

Error Analysis13m

Error Metrics for Skewed Classes11m

Trading Off Precision and Recall14m

Data For Machine Learning11m

Prioritizing What to Work On3m

Error Analysis3m

Lecture Slides10m

Machine Learning System Design10m

Section

Support vector machines, or SVMs, is a machine learning algorithm for classification. We introduce the idea and intuitions behind SVMs and discuss how to use it in practice.
...

6 videos (Total 98 min), 1 reading, 2 quizzes

Large Margin Intuition10m

Mathematics Behind Large Margin Classification19m

Kernels I15m

Kernels II15m

Using An SVM21m

Lecture Slides10m

Support Vector Machines10m

Section

We use unsupervised learning to build models that help us understand our data better. We discuss the k-Means algorithm for clustering that enable us to learn groupings of unlabeled data points....

5 videos (Total 39 min), 1 reading, 1 quiz

K-Means Algorithm12m

Optimization Objective7m

Random Initialization7m

Choosing the Number of Clusters8m

Lecture Slides10m

Unsupervised Learning10m

In this module, we introduce Principal Components Analysis, and show how it can be used for data compression to speed up learning algorithms as well as for visualizations of complex datasets.
...

7 videos (Total 67 min), 1 reading, 2 quizzes

Motivation II: Visualization5m

Principal Component Analysis Problem Formulation9m

Principal Component Analysis Algorithm15m

Reconstruction from Compressed Representation3m

Choosing the Number of Principal Components10m

Advice for Applying PCA12m

Lecture Slides10m

Principal Component Analysis10m

Section

Given a large number of data points, we may sometimes want to figure out which ones vary significantly from the average. For example, in manufacturing, we may want to detect defects or anomalies. We show how a dataset can be modeled using a Gaussian distribution, and how the model can be used for anomaly detection.
...

8 videos (Total 91 min), 1 reading, 1 quiz

Gaussian Distribution10m

Algorithm12m

Developing and Evaluating an Anomaly Detection System13m

Anomaly Detection vs. Supervised Learning7m

Choosing What Features to Use12m

Multivariate Gaussian Distribution13m

Anomaly Detection using the Multivariate Gaussian Distribution14m

Lecture Slides10m

Anomaly Detection10m

When you buy a product online, most websites automatically recommend other products that you may like. Recommender systems look at patterns of activities between different users and different products to produce these recommendations. In this module, we introduce recommender algorithms such as the collaborative filtering algorithm and low-rank matrix factorization....

6 videos (Total 58 min), 1 reading, 2 quizzes

Content Based Recommendations14m

Collaborative Filtering10m

Collaborative Filtering Algorithm8m

Vectorization: Low Rank Matrix Factorization8m

Implementational Detail: Mean Normalization8m

Lecture Slides10m

Recommender Systems10m

Section

Machine learning works best when there is an abundance of data to leverage for training. In this module, we discuss how to apply the machine learning algorithms with large datasets....

6 videos (Total 64 min), 1 reading, 1 quiz

Stochastic Gradient Descent13m

Mini-Batch Gradient Descent6m

Stochastic Gradient Descent Convergence11m

Online Learning12m

Map Reduce and Data Parallelism14m

Lecture Slides10m

Large Scale Machine Learning10m

Section

Identifying and recognizing objects, words, and digits in an image is a challenging task. We discuss how a pipeline can be built to tackle this problem and how to analyze and improve the performance of such a system.
...

5 videos (Total 57 min), 1 reading, 1 quiz

Sliding Windows14m

Getting Lots of Data and Artificial Data16m

Ceiling Analysis: What Part of the Pipeline to Work on Next13m

Summary and Thank You4m

Lecture Slides10m

Application: Photo OCR10m

4.9

started a new career after completing these courses

got a tangible career benefit from this course

By EL•Apr 28th 2017

Though there were some deficiencies, the course is very user-friendly, explanatory and highly diverse. In the course there are references to many subjects, which the professor explains simplistically.

By DD•Oct 13th 2016

I want to say that this is the first course I take on line. The experience is good. Thanks to professor Andrew, i got this opportunity to entering AI field. I hope this is the turn point of my career.

The Leland Stanford Junior University, commonly referred to as Stanford University or Stanford, is an American private research university located in Stanford, California on an 8,180-acre (3,310 ha) campus near Palo Alto, California, United States....

When will I have access to the lectures and assignments?

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.

What will I get if I pay for this course?

If you pay for this course, you will have access to all of the features and content you need to earn a Course Certificate. If you complete the course successfully, your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile. Note that the Course Certificate does not represent official academic credit from the partner institution offering the course.

What is the refund policy?

Is financial aid available?

Yes! Coursera provides financial aid to learners who would like to complete a course but cannot afford the course fee. To apply for aid, select "Learn more and apply" in the Financial Aid section below the "Enroll" button. You'll be prompted to complete a simple application; no other paperwork is required.

More questions? Visit the Learner Help Center

Coursera provides universal access to the world’s best education,
partnering with top universities and organizations to offer courses online.