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....

Mar 31, 2018

Perhaps the greatest instructor and the greatest course, I enjoyed it so much I had continued to do it in between my exams and looking forward fto start or deeplearning,ai specialization in a few days

Aug 19, 2017

Very helpful and easy to learn. The quiz and programming assignments are well designed and very useful. Thank Prof. Andrew Ng and coursera and the ones who share their problems and ideas in the forum.

篩選依據：

創建者 Mehdi A

•Feb 25, 2018

Too many trainings and assignments without enough practice, exercise and examples. This can be very confusing for a person taking the course for the first time.

創建者 Nicholas D

•May 14, 2019

Truly an exceptional class. Not often will someone with a deep proficiency in a discipline have the time or incentive to share their insights and teach to others; this class is a rare exception, and given the vital importance of machine learning to the future, I have a great appreciation and debt to Andrew Ng.

創建者 Simin L

•May 14, 2019

Great class! Should be recommended for every individual who wants to learn machine learning and don't have time or oppotunity to take a class at their own univerisity, this class is a guidance for the basis of machine learning and gives me instructions where to go next. Thank Ng really much.

創建者 Yash B

•May 25, 2019

This course was very well taught. There was a impressive focus on the basics and fundamentals of each topic. The lecture slides encapsulates the topics well and thus there was no such need of making my own notes which speeded up the learning process ;).

創建者 Miguel Á A S

•Jul 24, 2019

This course is one of the most valuable courses I have ever done. Thank you very much to the teacher and to all those who have made it possible! I will recommend it to all those who may be interested.

創建者 Fernando A H G

•Jul 21, 2019

Exceptionally complete and outstanding summary of main learning algorithms used currently and globally in software industry. Professor with great charisma as well as patient and clear in his teaching.

創建者 Rafael L d C

•Jul 19, 2019

Amazing course. It gets deep into the content and now I feel I know at least the basics of Machine Learning. This is definitely going to help me on my job! Thanks Andrew and the mentors of the course!

創建者 Cesare C

•Jun 20, 2018

good course; just 2 suggestions: improve the skew data part (week 6) and furnish the formula to evaluate the number of iteration in the window from image dimension, window dimension and step (week 11)

創建者 anand

•Nov 11, 2017

Great teaching style , Presentation is lucid, Assignments are at right difficulty level for the beginners to get an under the hood understanding without getting bogged down by the superfluous details.

創建者 Anup B D

•Apr 22, 2017

Very good coverage of different supervised and unsupervised algorithms, and lots of practical insights around implementation. All the explanations provided helped to understand the concepts very well.

創建者 claire.hou0701@gmail.com

•May 18, 2019

sehr gut!

創建者 Ganesh K A

•May 16, 2019

If it was in python, then it would have got 5 star from me.

創建者 Marcin K

•Mar 02, 2018

The course covers a lot of material, but in a kind-of chaotic manner. There is a lot of math, so if you're not familiar with linear algebra you may find it really difficult. Personally, I don't quite understand the approach. The goal of this course seems to be to teach people how the algorithms work, and if so - there is just enough math, for the students to get lost, but not enough of it to truly understand what's going on internally in the algorithms.

Also, the vectorization techniques of the provided formulas is not quite well explained, and it's left to the students to figure it out. This lead me a lot of times to trial and error approach, when I was just trying different approaches until something worked, but it was still hard for me to understand what really happened. Oftentimes I found myself spending more time on trying to understand how the matrices and vectors are being transformed, than actually thinking how the algorithm works and why.

Another thing is that after finishing the course, you have almost ZERO experience with real-world tools you're supposed to use for real-world projects. I'm thinking TensorFlow, R, Spark MLib, Amazon SageMaker, just to name a few.

On the bright side, the course teaches several general good practices like splitting the datasets to training, cv and test. It also explains very well how to work with different ML algorithms, how to monitor they are "learning well", and how to fine-tune their parameters or tweak the inputs, in order to gain better results.

The course ends with assuring students that their skills are "expert-level" and they are ready to do amazing things in Silicon Valley. That is obviously not true for the reasons I already mentioned (e.g. lack of tooling experience). I see this course as a starting point for anyone who seriously wants to go into ML topics, and to actually understand at least some of the internals of the 3rd party libraries he'll end up using. But don't think you'll end this course with any practical knowledge, or that you'll be ready for real-world problem solving.

創建者 トミー ペ

•Feb 03, 2019

This course was very difficult, coming from a non-math/matlab background, but did teach me a heck ton about the world of machine learning, for which I am eternally grateful. Life got in the way big time, and it took a lot of time and energy to complete the programming exercises. There was also a lot I didn't understand, and I did wish there was maybe another week of getting used to certain concepts, particularly maths issues like double summing. I appreciate that this would complicate things though. I found that I am not geared towards the forums - my learning style involves conversation and not really experimenting on my own (which I can do once I understand a concept). As helpful as the mentors were, only relying on the forums with my time schedule meant that that taking this course dragged on longer than I would have liked. I also got a bit overwhelmed by the lack of centralised information. I know that it would require a complete overhaul to sort such out, but it did make looking up information time-consuming. Nevertheless, I am grateful for all that I learnt, and appreciate that I plunged into the deep end. I don't understand everything, and of course a little knowledge is a dangerous thing, but I know enough to know what to refer to should I ever need ML in my next job. Thank you.

創建者 David C

•Apr 02, 2019

Have to give a star so I will give it one. Others rate this course highly. I don't know why.

Course states no requirement for knowledge of linear algebra. However this is not really practical and seems disingenuous. I have spent a lot of time re-learning linear algebra.

I have spent much more time on the work than the course states and unless you are currently involved in similar work you probably will too.

I have never received any response to the feedback I provided.

Many times I have been frustrated because the math material is treated casually but then later success on quizzes and assignments are based how well you understand the math. So while the instructor and content can treat the math as casually as they wish, unfortunately, you cannot be so casual.

創建者 Kevin M

•Dec 14, 2019

This is a terrific class! The Course is well structured in terms of videos, invideo pop-up quizzes, course notes, programming exercises, and the discussion boards & mentor community. The 11 weeks includes 8 programming exercises, with usually 5-6 "code submittals" per exercise.

The option of OCTAVE or MATLAB is great (I used MATLAB). A key aspect of this course is using vectorized methods in every programming assignment. There was always an option to write a procedure approach (e.g. do loop for summation steps like sum of squared differences for gradient descent or linear regression). The computational advantage, the simplicity of using vectors, and ending with "crisp" code is a great step

I have completed a similar class from MIT (Python or R based) and the exercises in this class were far superior in reinforcing the course materials.

This journey takes you through Supervised Learning models leveraging Linear Regression, Logistic Regression, Neural Networks, and Single Vector Machines and how gradient descent is the cornerstone to determine the theta values needed to optimize your hypothesis. Unsupervised Learning using K-means, PCA, and Anomaly Detection. Specific real life example for Recommender Systems, Character Recognition and large scale machine learning.

The various topics on "advice" by Professor Andrew Ng is invaluable. Understanding how to measure performance of your algorithm is key. Underfitting (bias) and over fitting (variance), regularization, learning curves, evaluation (precision, recall, and F1), and error analysis. Of particular note, is his understanding how to objectively determine how to what to work on next and how to apply "ceiling analysis" in complex pipeline ML applications.

A final note, the course mentors are unbelievable! Tom Mosher and Neil Osgrove are truly special. Their understanding of the material, their patience, and their incredible responsiveness is highly beneficial to the learning experience. You have to do the work and figure it out, but the mentors are there to help you navigate the Machine Learning journey!

創建者 John H

•Aug 22, 2019

This have been a very good and comprehensive introduction to Machine Learning, IMHO. It have given me the all basic introduction to ML that I could have hoped for. (I'm a senior practitioner of many forms of mathematical modelling and programming, as a former Astrophysics Phd.)

In particular, Andrew Ng is an excellent and experienced lecturer, and it's something that shows in that the course have been tested on thousands of students and over long time, such that for example exercises work very well in every little detail. (Sometimes quizzes may seem a little picky having to get nearly every little question right - but it's for really getting the understanding solid, and you can always improve your grade.)

Therefore, this must be a very good choice as an ML introduction, provided that you're willing to put in the effort of a few weeks on full time. (Albeit 11 weeks is for 'normal' university study schedule, and the course can be completed much faster on full time.) It should also compare well in generality compared to other courses (like Googles Machine Learning Crash Course).

創建者 Mark M

•Aug 11, 2016

Professor Ng is a great teacher, his course is both challenging and satisfying. The exercises require you to take one step beyond the lecture -- not just parrot back the transcript -- you have to think about the implications of what you've just studied. Yet Ng's presentations are lucid and informative and that next step is obvious, once you think about it.

My greatest challenge is that, although I have been programming for decades, I've only dabbled in a functional language like Octave and my last math class dates back to the 70s. However, the math requirements are not onerous and I'm struggling through the Octave assignments with some success.

Although the course is 11 weeks there are more than 16 lectures as some weeks have two complete sets of lectures PLUS there are assignments every week that take a few hours to complete. So while there is a little more work in this course than in other Coursera offerings there is great value for the money and time spent.

If you're interested in Machine Learning this course is a great place to start.

創建者 Ozgur U

•Jan 06, 2020

This is the first course I ever took on Machine Learning. I have a good background in linear algebra. Therefore, Mathematical aspects of the course was not a big challenge for me. At the same time, Professor Ng explains the ideas behind each ML algorithm in an easily comprehensible manner. It is easy to follow his videos except the sound quality. I would strongly recommend that they improve sound quality.

The quizzes are not very challenging and easily doable if you understand the lectures.

The assignments are easier than I expected. The whole structure of the algorithm is given to you and some parts of the assignments simply require writing one or two lines of codes. I would recommend them adding a capstone project at the end of the lectures so we can apply what we learned.

Overall, if you are looking for a fundamental introduction to ML and posses a basic knowledge in college level linear algebra, I would strongly recommend this course to you.

創建者 Vikrant K

•Aug 30, 2019

It's so wonderful that it can't be explained by the words and at the same time i am very sad that Ng sir has left us . i just love Ng sir , He is so wonderful person and teacher that can't be explained by the words .It's quite bit a big dream but i am dreaming of some day in the future where i am working with Ng sir on some machine learning problem and he is guiding me as he is doing now . I just love the course and also the mentors Mr. Neil Ostrove and Mr. Tom he had helped us to complete this course and assignment and also solved my useless something baby problems more carefully and i will help other student as guided by Ng sir in completing this course smoothely . and that's all . at the last i want to tell I just fall in love with Ng sir and coursera and the team . i have a big dream of meeting that my favourite Ng sir on some day.

Thank you

創建者 Luca W

•Jan 19, 2017

Thank you Professor Ng for taking the time to produce such a phenomenal course. As mystifying as machine learning can appear to be, your well-paced and digestible teaching style gave me the opportunity to understand. With fantastic lectures, mid-video quizzes, end of topic quizzes, and programming assignments, you as a student are given all the resources you need to absorb the material.

These eleven weeks really gave me the perspective and knowledge I sought for. This is the first online course that I have taken and I am inspired and excited for the future of machine learning and e-learning. The final heartfelt video was a perfect conclusion and I wish to return the sentiment of gratitude and appreciation.

Thank you again, and rest assured that your teaching is having a profound impact on peoples lives across the world.

創建者 Tobias T

•Jun 05, 2019

I've tried DataCamp and recently take my first course in Coursera. The difference is huge and important if anyone wish to learn more about ML or DS. This course does not focus much on 'just coding' the answer. It aims to teach you the logic, basic maths behind ML algorithms.

The coding exercise is challenging and fun aswell. It doesn't give you any 'fill in the blanks', so basically, after each exercise, you properly have some good understanding about the logic. Using Matlab/Octive is much better than I expect. Not that it is easy to use/understand, but it let you understand the Math better. e.g. when to transpose, how to use look at dimension before writing any codes. These exercises are at a level which you can easily transcend your understanding and knowledge to whatever Python or R you are using. !

創建者 Vincent C

•Sep 25, 2019

After finishing the course, I feel much more confident in pursuing more advanced machine learning. The course teaches everything intuitively and in detail but maybe it could use some improvement to achieve perfection. It would be better if the course could provide pointers to some of the topics beyond the scope of the course such as the derivation of the back propagation, svm, pca, etc. Because often times when you search for derivations they might not be very useful for your levels, if course could provide some good references as some lecture notes after the video would be great for the students to gain even more solid groundings of the things behind the hood

Super thanks and thumbs up

創建者 Vamshi B

•Jun 06, 2019

As a machine learning newbie, I can say this course is really helpful to get in depth intuition on how machine learning algorithms work. Techniques to evaluate and improve our algorithms are also explained very well. Programming exercises are really challenging. Review questions are also crafted well. Though this course uses Octave/Matlab instead of python for programming, I find it quite useful to understand and implement algorithms easily. Only negative of this course is, mathematics involved is not explained in detail. Overall, this course has helped me a lot to understand machine learning in a better and useful way.

創建者 DEEPANJYOTI S

•Mar 11, 2019

This is a very good course which gives a good solid foundation in the basics concepts of Machine Learning. Prof. Andrew explains reasonably complicated algorithms in a very intuitive way which goes reasonably deep, but at the same time doesn't overwhelm the student with a lot of underlying mathematics. The course structure also follows a very natural progression (linear regression --> logistic regression --> neural network --> SVM) and bringing in other basic concepts like feature normalization, regularization, measurements etc. along the way. Definitely one of the better designed courses I've seen so far.