In the third course of the Machine Learning Specialization, you will: • Use unsupervised learning techniques for unsupervised learning: including clustering and anomaly detection. • Build recommender systems with a collaborative filtering approach and a content-based deep learning method. • Build a deep reinforcement learning model. The Machine Learning Specialization is a foundational online program created in collaboration between DeepLearning.AI and Stanford Online. In this beginner-friendly program, you will learn the fundamentals of machine learning and how to use these techniques to build real-world AI applications. This Specialization is taught by Andrew Ng, an AI visionary who has led critical research at Stanford University and groundbreaking work at Google Brain, Baidu, and Landing.AI to advance the AI field. This 3-course Specialization is an updated and expanded version of Andrew’s pioneering Machine Learning course, rated 4.9 out of 5 and taken by over 4.8 million learners since it launched in 2012. It provides a broad introduction to modern machine learning, including supervised learning (multiple linear regression, logistic regression, neural networks, and decision trees), unsupervised learning (clustering, dimensionality reduction, recommender systems), and some of the best practices used in Silicon Valley for artificial intelligence and machine learning innovation (evaluating and tuning models, taking a data-centric approach to improving performance, and more.) By the end of this Specialization, you will have mastered key concepts and gained the practical know-how to quickly and powerfully apply machine learning to challenging real-world problems. If you’re looking to break into AI or build a career in machine learning, the new Machine Learning Specialization is the best place to start.
TF
I hope more and more engineers in Japan take this course.The joy of learning machine learning with the world's top lecturer far outweighs the pain learning the subject in the non-native language.
SA
Thank you so much this is a great course, and thanks for the financial aid that enabled me to study the course and improve my skills and career. this specialization is so valuable and useful.
MW
Andrew was a great teacher, explaining complicated topics in a simple and intuitive way. The programming assignments helped to put theory into practice. A great place to start learning a new field!
KA
This is an excellent introduction to supervised learning and reinforcement learning. It's an excellent course for any beginner in this field. Very easy to follow and very much enjoyable!
AS
This is a good beginner course . I have been reading around topics and when you jumble around it is hard to follow. This course structure was what i was looking for. i would recommend this to others
GR
The course has been very informational, and even though it had some complex topics, it never felt too complicated to understand as all the explanations and examples were really great.
MK
So much time to spend, so much math to understand, but it's really fun to gain knowledge from this course especially machine learning intuition for me who had passion on that. Thankyou!
HA
The content was details, explained thoroughly and understandable. But, when it came to implementation, few more labs similar to the structure of previous course could have improved it more.
TK
It simply exceeded my expectations. I recommend it to whoever who is trying to learn the concepts and need tips related to industry practices, and overall wants an applied approach.
AV
Amazing content, perfectly curated topics with hands-on labs, although Assignments and labs could be more challenging based on certain level students who already have programming backgrounds.
RJ
clear, concise, well explained and best labs. this course is best starter for machine learning ( unsupervised).thank you for Andrew Sir, and whole team for sharing your knowledge.
MS
lecture videos, practical labs, and last video (conversations with andrew), all are awsome. Thank you for giving me a solid intuition about unsupervised learning and reinforcement learning
显示：20/871
week 2 and 3 left me with a feeling of a very partial understanding of the material
While the material presented in this course was very interesting, and Andrew Ng was delightful, there was SO MUCH repetition, redundancy, and basic (yet unnecessary) math that the content could be condensed to about half the length, and anything that falls into "don't worry about it" category could be made optional. Personally, I would have preferred having to worry about it - yes, people should expect to learn and use math in these technical courses.
The quizzes were inane, truly, with the answer sometimes right there in the questions, and practice labs required minimal thought, sometimes just copying code from sample labs or lecture notes. Overall, testing materials in this course were way too dumbed down, which was disappointing.
The best thing this course did for me was to remove the enigma of machine learning. This specialization is not so much about going deep into individual machine-learning algorithms and techniques as it is about exposing a student to the broad spectrum of all the different kinds of problems for which machines can be programmed to learn a solution. Once a student completes this course, they have a very good idea of the kinds of problems that can be solved by letting machines learn how to solve those problems and specific algorithms/techniques that need to be used for that particular kind of problem. A student can then research additional resources for the specific problem they have at their hand and take a deep dive into developing a working solution for their specific problem. This course enables you to start that journey by taking away the fear created by the belief that machine learning is something very challenging.
The video explanations are amazing, but the practical exercises are just frustrating. The difficulty is fine, could be more challenging actually and also require you to do more than what was explained in the videos. The annoying part are the unit tests. I almost always get a fail even though my functions return the expected output. I have compared my function to the solution and I always get the same results. I do not know how the unit tests are designed but they do not fulfill their purpose. It is frustrating that I have to write functions in a pre-dedfined way to get a pass even though my function generates exactly the same output. Even more frustrating that the explanatiosn in the notebooks do not explain why the function has to be written exactly in that way, when a more efficient way with less or even no for loops is possible. I would recommend to rather play around and write your own classes on your local machine and compare output to scikit-learn algorithms. I think you learn more that way than having to resort to copy pasting code to get a pass on the unit tests....
One the positive side, the course materials are well explained and up to date. As a negative point, the practical labs are not really challenging, with only a few lines of code to be written, the rest is already given - this leaves up to the student to take the time to go through the rest of the code to really understand the methodology.
So much time to spend, so much math to understand, but it's really fun to gain knowledge from this course especially machine learning intuition for me who had passion on that. Thankyou!
This is a great start on machine learning, And I think the great Attitude of Mr.Ng in explaining things clearly and succinctly is amazing. I only hoped that there were more and smaller programming assignments, slowly building up to the current ones we have, where we would write things from scratch. Towards the end, the programming assignments were getting complicated, but the tasks asked from the learner stayed relatively simple, and I didn't as much of deep involvement in the programming as I would have. Thank you for this great course. I learned a lot!
I feel that the part about reinforcement learning was a little confusing to me regarding the algorithms. i suggest adding an optional lab that lets the user experiment with the code and that prints out what the variables are, to get a better intuition of what it is we are actually doing. i think this was done very well throughout the specialization, but that it was lacking in the reinforcement learning part. thank you
Good general introduction but superfacial, and with too many small errors in the video contents.
Out dated code used so if you want to follow along you cannot. So many other concepts not covered in the videos requiring you to self learn. That defeats the purpose of doing this course, which is supposed to teach you. Coursera community advisors are not paid?? If this is so then shame on Andrew Ng as this course must rake in a lot of money. Maybe take some of this money and pay the community staff and pay someone to update the code. Disappointed.
Thanks Andrew Ng and Team!!
the courses are beautifully explained, and the lab are greatly prepared and organized!
I have wanted to follow this course for a long time, and I am very grateful that finally, I had some time to make it!!!
Special message to Andrew Ng: you make this course very special and exceptional! Indeed, your compassion and concerns to make the world a better place are refreshing in today universe. You really make the world better by sharing knowledge in a great way. I wish you all the best in your multiple endeavors :-)
Fabrice
This course is a brief but thorough introduction. It has a good mixture of theory and practice.
Andrew Ng explains every thing very good, understandable and in a fun way.
I highly recommend this class!
Andrew was a great teacher, explaining complicated topics in a simple and intuitive way. The programming assignments helped to put theory into practice. A great place to start learning a new field!
It simply exceeded my expectations. I recommend it to whoever who is trying to learn the concepts and need tips related to industry practices, and overall wants an applied approach.
This course is an excellent course for introductory machine learning. All of the topics are covered in great detail and It is an honor to be taught by Andrew N.G, the Great teacher.
Great course and very well taught by Andrew! The only problem is that now I am left with a burning desire to learn even more and start applying all this knowledge everywhere ...
Awesome specialisation. Allowed me as a beginner to get a good initial understanding of machine learning and put begin to put concepts into practice.
Excellent Intro to ML topics, I'm grateful to have taken this course and the explaning way for dummies of Andrew Ng. Towards ML Engineer ->
Enjoyed the specialization as a whole, but part 3 seemed to cover ground too quickly. I think more practice would be beneficial with more labs and perhaps there needs to be a 4th course to spread this content out or otherwise cut some out. Still 4 stars because it does give a wide overview but it felt superficial and if an overview was the goal it should have shown less theory and formula as this just made me feel like I wasn't getting it.
weakest of the 3 courses
hardly any optional labs, the graded practice labs were too easy