Chevron Left
Zurück zu Maschinelles Lernen

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

4.9
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....

Top-Bewertungen

AD

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.

MN

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:

25726 - 25750 von 27,242 Bewertungen für Maschinelles Lernen

von amit j

May 28, 2017

very good course material

von David R

Aug 14, 2015

The Good: This course is a good introduction to fundamental topics and basic techniques in machine learning. I feel that the biggest strength of this course comes from Prof. Ng's suggestions for how to design and improve machine learning systems in practice.

The Bad: This course is a few years old, and there are a lot of errors in the videos and even occasionally in the programming exercises as well. In my opinion, there is a little too much hand-holding in the programming exercises, so that while I was able to implement the important bits and pieces of the algorithms, I didn't get much chance to practice the more difficult task of organizing the entire system.

The Ambiguous: This course is *very* light on the math, perhaps as light as you could possibly get. I imagine this is a relief for a lot of people, but personally I felt annoyed and even a little patronized with the number of times Prof. Ng said that we "don't have to worry" about the mathematical details of different concepts and algorithms. It's fine to skip over derivations and details for the sake of a simple presentation or to emphasize practical application, but surely it is important to go back and see what all this stuff means eventually. I will certainly be looking for other courses on machine learning that give a more mathematical treatment, and I think that anyone who wants to seriously get into ML should probably do the same. On a related note, Prof. Ng takes his time in each video, speaking slowly, repeating different points, and carefully explicating formulas with examples. For some people that may be good, but I found myself frequently skipping ahead in videos because I just wanted to get to the point.

von Kaushal S

Apr 07, 2016

Exceptional content and absolutely amazing tutor.

von Dhanush A M

Feb 29, 2016

Good course material for beginners in Data Science.

von Eric D

Sep 30, 2015

While the professor doesn't want to confuse the audience with proofs and calculus, I think it would be nice to have some extra videos that explain in detail the proofs and reasoning behind the different formulas used throughout the course.

von Sergey S

Jan 28, 2016

This course is good but not the best I've seen

von Shannon L

Nov 17, 2015

Very good course with a lot of hands-on, direct-to-application assignments. It is fairly introductory, so all you need is first year calculus, which in itself is not bad but this course is fairly theory-light. The theory that is included is just enough to be able to refer to further theory not covered.

von NGUYEN K T

Jun 27, 2016

great course

von Xinpeng H

Jul 21, 2017

Good introductory course. Assignments are too easy.

von Dan-Timon R

Apr 12, 2017

Great course! SOmetimes a bit lengthy, especially when explaning really basic concepts (which should be known by most people) but still fun to watch. Lot to learn for beginners in machine learning.

von Ashwini M N

Mar 07, 2018

I had fun and learnt a lot about machine learning. Andrew Ng makes the topic very interesting and guides really well.

von Akhil P

Dec 01, 2015

Prof Andrew Ng did an extremely amazing job, he took the effort to not leave out even many obvious details. He ensured everyone was following the course, and the course itself has covered many aspects of supervised learning etc. It works as a great introductory course for someone who is new to the paradigm and would be the first step if someone is interested in pursuing research interests in the field

von Michael B

Dec 24, 2015

Overall, an excellent course. Well organized and taught. MatLab/Octave homeworks can be tedious but thats coding for you.

von David M

Dec 27, 2016

Good introduction to machine learning with many examples and assignments.

von Guangxiang Z

Aug 08, 2016

The course is very good,throgh taking this course,I have a general picture about machine learning .But ,there still exsists several problems,for example,the quality of the videos are low,and I am really looking forward to new version of the course.

von João M

Nov 02, 2015

Hello, the course is great. Only one suggestion is to go a little bit deeper in subjects such as SVM optimization techniques or PCA mathematical background. At least a good set of references could be suggested for the interested s

von Nick S

Oct 08, 2015

Indepth technical introduction to machine learning and its related concepts.

von Sanchayan M

Dec 24, 2016

This course is great at covering the fundamentals of Machine Learning at an intuitive level and not going heavy on Mathematics of it. When it comes to the example assignments though, I prefer the hands on approach of the Udemy course Machine Learning A-Z™: Hands-On Python & R In Data Science. I guess I just do not like Octave somehow and prefer the Python approach coming from an Embedded/Programming background. Taking both the courses side by side is just perfect for getting started with Machine Learning and covers both theoretical and practical aspects for starters like me. Anyways hats off to Mr. Andrew for this course. Thank you.

von Lorenzo B

Nov 14, 2016

Interesting stuff, and quite comprehensive. However, the programming assignments on a "fill here" basis does not really lead to a generalization of the required algorithms to perform ML.

von Alberto B

Sep 28, 2015

Very nice, the only bad thing is that the instructor uses Octave/Matlab, It would have been nice if he have used Python instead.

von Andrea M

Aug 05, 2017

Very nice. I would have loved some mathematical appendix with more details but I really had lots of fun on a number of interesting topics

von Christopher P

Feb 13, 2018

Good overview of machine learning as a subject. Introduces terminology and Andrew NG is very clear about what aspects of his lectures are necessary and what aspects are a deeper dive for enthusiasts.

von Jacob N

May 31, 2016

Good course but a little light on the theory, especially on SVM's

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.).