Chevron Left
Zurück zu Maschinelles Lernen

Kursteilnehmer-Bewertung und -Feedback für Maschinelles Lernen von Stanford University

114,367 Bewertungen
28,116 Bewertungen

Über den Kurs

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....



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.


Oct 31, 2017

Great overview, enough details to have a good understanding of why the techniques work well. Especially appreciated the practical advice regarding debugging, algorithm evaluation and ceiling analysis.

Filtern nach:

25751 - 25775 von 27,244 Bewertungen für Maschinelles Lernen

von Corey S

Jun 09, 2017

Just about perfect. The only negative thing I can say is that I feel like the practical aspects of how to apply the ML techniques was lacking. The programming exercises were couched in terms of real-world problems, but so much of the focus was on understanding the math behind the machine learning algorithms that the details of how to setup a problem and solve it via ML were somewhat lost. With so many toolkits available today to perform the math parts of the work, it seems to me that the practical application of the techniques is more important than the math and I would have liked more focus in that area.

von Michael S

Oct 06, 2016

Good overview, but less theory. Would also maybe be good to have had a section on starting from a problem and how to select a technique (supervised learning, unsupervised learning, etc.).

von Nate A

Jun 06, 2017

Great course and subject. The videos where well done and the exercises had just the right amount of difficulty.

von Robert N

Jun 23, 2018

Hands-down the most focused and refreshing introduction to the buzz that is statistics on steroids.

von Luka K

Nov 10, 2016

Great class from practical point of view. It would be great if there where more videos with derivations.

von Dixit P

Oct 19, 2016

This course provides sufficient knowledge to understand a lot of jargon related to ML.

von Bernardo F B B

Jun 27, 2016

The course is exceptional. However there are many errata that could be corrected but Coursera refuses to do so.

von Aadesh N

Jan 24, 2016

This was best course till I took Machine Learning from University of Washington

von Ludwig P

Aug 13, 2016

Very good introduction to machine learning. The content is fairly basic, it's up to you is you want to go deeper into the subject.

Only one downside, the quality of videos is low.

von Ajay K

Jul 12, 2017

The course was a good introduction on machine learning and the associated math in a simple and lucid manner. More mathematical rigor could have been introduced in some concepts.

von rahul s

Nov 22, 2017

This is a very easy to understand and well informative course with very good examples for each of the topics. The best part is you get to see a few very interesting cases where machine learning just hits the bull's eye, which keeps you motivated throughout the course. Overall, the course is neither too mathematical nor too much formula based, it has a good balance between two.

von Igor R

Sep 07, 2017

Nice introductory course. Was expecting a bit more advanced maths, etc., but I guess one has to make compromises. Very interesting tips on performance analysis of machine learning algorithms.

von vaibhav n

Jun 19, 2017

A good introductory course that isn't too heavy on math. Programming assignments are pretty easy too. I'd enjoy the course more if the math were more involved. At the very least, this course will give you a qualitative understanding of the basics of machine learning. The (ungraded) additional resources are great if you like getting into the details of what you're learning and you'll learn much more if you read them. You'll probably finish this course in a couple of weeks if you're accustomed to college level math.

von Kanahaiya G

Aug 29, 2017

Its a good course for beginner. But at some places its difficult to understand what is happening.

some topic can be explained better i feel like week 10.

Overall its a good kick start for ML

von Zeimer

Sep 03, 2017

A good introductory course, but there are two issues:

1. The programming exercises are a bit dumbed down (you mostly fill in code fragments rather than write everything from scratch, which could make you miss a few points about how it all works).

2. Professor Ng at the end tells you that "now you are expert in machine learning". This is a lie.

von Aliaksandr K

May 15, 2016

some weeks are really easy and understandable, but some which consist of 2x number of lessons are far more challengable, moreover the topic during such weeks may be also way more harder. i would really consider somehow redistribute tasks/lessons to make all weeks of a similar level of understandability and possessing the same number of video lessons.

overall it's a really great course though

von Sazzadur R

Jul 30, 2016

One of the most thorough and effective online courses in Machine Learning


Jun 24, 2016


von Mengqi C

Aug 17, 2015

A good introductory course for newcomer in Machine Learning.

von Matthieu V

Oct 20, 2016

Really nice course, but the quizzes kind of take much from the examples presented in the lectures, so it seems to me like learning by heart would be somehow enough to get the grades. Comprehension could be more emphasized in the tests. Said another way, I found the quizzes to be rather easy (some questions were tricky, but many seemed to me rather obvious).

von Ashvin L

Dec 05, 2016

This is a basic course that will provide good fundamentals in ML. If you are already a student with advanced degree in Mathematics/Engg or a professional with decade of experience might find the class a bit slow. However, it was well worth it.

von Dhruvil B

Aug 18, 2015

Great course. Would have liked to have a final project and some more in-depth videos for the mathematics of some of the algorithms. Slides/notes for each lecture or unit or week would be extremely helpful for those who take the class in the future or for those who have finished and would like to review the material. The programming assignments were very interesting and close to the real world. Enjoyed the course overall.

von Padmaja B

Jan 17, 2017

Very informative and a good course

von Vineet R

Dec 03, 2016

A very good experience till now.

von Roman

Feb 22, 2018

That was a very good introduction into main ML topics.