Link to Content:

Coursera

Created/Published/Taught by:

Andrew Ng

Stanford

Content Found Via:

Stanford Online Courses

Free? Yes

Tags: best practices / bias / clustering / cost function / deep learning / dimensionality reduction / gradient descent / kernels / linear algebra / linear regression / MATLAB / matrices / neural networks / non-parametric algorithms / Octave / parametric algorithms / recommender systems / supervised learning / support vector machines / unsupervised learning / vectors

Difficulty Rating:

Description from Coursera:

“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.”

Recommended Prerequisites: None Required;

Recommended: college-level math (calculus, statistics), familiarity with linear algebra, familiarity with computer programming

Go to Content: Machine Learning (Coursera)

## By Henry Wolf October 20, 2015 - 8:05 pm

The professor for this course is better than most, and is currently working at Baidu, but the videos are pretty slow-paced. The material is pretty good, but the homework assignments could be better designed.

Advanced Beginner- familiar with data science / new to this topic / some prerequisitesAdvanced Beginner - was new to this topic / had some prerequisites

(2) A Little

No ratings yet.

## By rgap October 21, 2015 - 4:58 pm

I took the course and learned or mostly reviewed some techniques. I didnt like all the octave homeworks. And I think it’s much better if after taking the course you also take the real one from stanford http://cs229.stanford.edu/

Intermediate- comfortable with data science / has relevant prerequisites / familiar with this topicAdvanced Beginner - was new to this topic / had some prerequisites

(4) A Lot

Detailed Content Survey:Required for school or in order to keep or be eligible for a job

I have used content from this publisher/series before

Yes

All of it

just basic linear algebra

octave, matlab

Maybe this one

https://www.khanacademy.org/math/linear-algebra

Learned the math behind ML

How a basic concept thats part of a basic technique is generalized and becomes part of another more complex techniques

The homeworks

Use my class notes http://relguzman.blogspot.pe/2015/03/coursera-machine-learning-class-notes.html?m=1 ;)

Just follow the course instructions

Like 6 weeks

students who start learning about ML

http://cs229.stanford.edu/

## By monraf October 26, 2015 - 6:33 am

This was a very good course allowing for the student to learn a lot about basic machine learning. To get the most out of this course the student should know some linear algebra and basic programming skills.

Intermediate- comfortable with data science / has relevant prerequisites / familiar with this topicIntermediate - had relevant prerequisites / was familiar with this topic

(4) A Lot

Detailed Content Survey:Wanted to learn just for fun / Looked interesting

I have used content from this publisher/series before

Yes

All of it

Linear Algebra, some calculus and programming skills

Matlab or Octave

Basic Machine Learning Skills

The exercises

Follow course requirements and instructions. Try give yourself time to complete homework exercises.

Completed the exercises as they occurred

6 weeks long and spent around 6-8 hours a week

Advanced Beginner

## By trianta2 November 10, 2015 - 2:45 pm

My background by degree is electrical engineering, so I already understood the mathematical and programming prerequisites for this class.

I watched all the lectures, and completed all the programming assignments and quizzes. I think Andrew is a great teacher, and his lessons and intuitions have been instrumental to my career development.

As with anything in life, the more you buy in, the more you’ll get out. Speed through lectures and hack the quizzes purely for scores, and you’ll get a crummy education. Buy in, do everything with thought and care, and you’ll walk away much more knowledgeable and capable.

For what it’s worth, I took this class in 2012, when I worked as a software verifier. With this knowledge (and the knowledge obtained in many other MOOCs which I completed with similar gusto), I now work in a telecom research lab and spend my time designing machine learning solutions.

Advanced Beginner- familiar with data science / new to this topic / some prerequisitesAdvanced Beginner - was new to this topic / had some prerequisites

(5) More than I even wanted to!

No ratings yet.

## By Bill Kimler December 9, 2015 - 1:18 pm

This 11-week course on Machine Learning was one of the most challenging I’ve encountered since graduate school It was heavy on the mathematics (especially Linear Algebra) and introduced me to a new mathematics software package called Octave (an open source rendition of MatLab).

This has been the most challenging course I’ve taken so far. The professor recorded 110 lecture videos on a wide variety of topics from basic linear algebra to pattern recognition in photographs to determine numeric digits. You will not be an expert in the subject after this course (after all, are you an expert in Physics after a single class?). But the notes I took and the challenging quizzes and lab exercises this course demanded will provide a wealth of material that I will be referring to for years to come!

Make no mistake – this is an advanced course. But this is where modern Data Science is at. You need to know this material if you’re serious about the subject.

https://dreamingofdata.wordpress.com/

Advanced Intermediate- comfortable with data science and prerequisites / has prior experience applying this topicAdvanced Beginner - was new to this topic / had some prerequisites

(4) A Lot

No ratings yet.

## By adj2312 April 28, 2017 - 12:01 am

This course is the basic building block of machine learning for newbies (Hello World! course in ML). Andrew Ng explains all the required concepts with proper explanation and reasoning. Course is to the point and well organized. Though one drawback for Software engineering background people is the assignments are in Maltlab/Octave. It will be better if you try porting these assignments in python and achieve the same results.

Early Beginner- new to data science / totally new to this topic / few prerequisitesEarly Beginner - was totally new to this topic / had few prerequisites

(4) A Lot

No ratings yet.