Created by:  Stanford University

  • Andrew Ng

    Taught by:  Andrew Ng, Associate Professor, Stanford University; Chief Scientist, Baidu; Chairman and Co-founder, Coursera

Language
English, Subtitles: Spanish, Hindi, Japanese, Chinese (Simplified)
How To PassPass all graded assignments to complete the course.
User Ratings
4.9 stars
Average User Rating 4.9See what learners said
Syllabus

FAQs
How It Works
Coursework
Coursework

Each course is like an interactive textbook, featuring pre-recorded videos, quizzes and projects.

Help from Your Peers
Help from Your Peers

Connect with thousands of other learners and debate ideas, discuss course material, and get help mastering concepts.

Certificates
Certificates

Earn official recognition for your work, and share your success with friends, colleagues, and employers.

Creators
Stanford University
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.
Ratings and Reviews
Rated 4.9 out of 5 of 35,096 ratings

One of the best courses that I have done. It's an amazing starting point for Machine Learning enthusiasts.

Would be better if some of the complex ML algorithms were explained in more simpler ways..

The course is very well structured and the programming assignments are challenging. I now feel that I know a lot about the topic and want to study further. The best part is that the course is quite detailed in most of the areas. Professor Andrew Ng is absolutely amazing. I am very happy. I should mention how I am getting job offers through LInkedIn after completing my course.

A good balance of theory and practice to get started with ML. I tend to be academic-oriented, so I often had to pause and go off reading up other sources (or other online courses) to be able to really understand the concepts in a intuitive way. On the other hand, the quick schedule and programming exercises of this course helped stay on track and pushed me forward. Octave was a fun tool to learn ML with but I imagine I will have to learn other programming languages after this course.

As for time-commitments on this course, some weeks are heavier than others (esp if you want to understand the theory deeply), and on average I spent 20 hours per week. Programming exercises were easy (for me) unless I had a bug, and then debugging was hard. For those who are academic-oriented like me, I highly recommend studying Linear Algebra in advance of this course.