Chevron Left
Zurück zu Maschinelles Lernen

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

4.9
120,940 Bewertungen
29,696 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

CS

Jul 16, 2019

The course will give you the incites to understand the data driven mathematical functions to write softwares that can behave or change its behavior, based on stimulus (data).\n\nAndrew Ng is excellent

QP

Jun 25, 2018

This course is extremely helpful and understandable for engineers and researchers in the CS field. Many thanks to the prof. Ng Yew Kwang for his great course as well as supporters in the course forum.

Filtern nach:

28476 - 28500 von 28,807 Bewertungen für Maschinelles Lernen

von theolaurensbos

Sep 26, 2019

It would be nice to, if this course is reevaluated, maybe align a little bit more towards the more popular programming languages. Not changing from Octave to, let's say Python, but to address the possibilities on how to solve the exercises using other languages. So people would learn what goes on under the hood of the popular ML packages in other programming languages.

von Miloš P

Oct 20, 2019

I really enjoyed the course but I wish it went into more detail with regards to math.

The math of backpropagation was a bit neglected, but I ended up deriving all the calculus myself so it wasn't a problem.

The math of PCA was severely neglected but I understand that it falls out of the scope of this course.

The major problem for me was that SVMs were very poorly explained.

I had to watch the MIT OCW and (Professor Andrew's) Stanford lectures on YouTube to get a more complete understanding of the subject.

Also, I really wish there were a large project assignment, but I understand that something like that couldn't be automated with a grader and served to thousands of students efficiently.

von Preethiya B

Sep 30, 2019

Good

von MianWang

Oct 01, 2019

It is a very useful class for those who want to apply machine learning to work, especially for new starters.

von Plinio L D A

Sep 30, 2019

In overall the course is clear and concise. One minor problem is due the fact that the videos need some editing; Andrew almost always repeat some parts of the videos when something goes wrong. I also missed the texts between each video in the last weeks.

von Srutimala D

Oct 21, 2019

I am now one step closer to understanding machine learning in terms of its inner workings and algorithms. I not only have a grasp on the algorithms but also intuition on how data quality and quantity has effect on the final model and how to improve models.

von Yash G

Oct 02, 2019

My idea of ML was to understand the concept and it helped me a lot. Was not expecting this much of coding.

von Tanmay G

Oct 02, 2019

Awesome Course To Form The Foundations Of Machine Learning. Really It Include Nearly A Student Need Regarding Machine Learning Algorithms Proofs Etc... Best Course For A Reason...

von Yinghao Z

Oct 03, 2019

It's a really amazing course for a rookie in machine learning. In this course, Andrew succeeded to decompose very complicated mathematical concepts and broke them down to the units that are very easy to understand. Although it contains lots of difficult mathematical formulas and notations, these are not that difficult and give student enough time to think over and deduce them by hand, I think this is an excellent part of this course - challenging but fun. Also, I love the programming exercises, it gives sufficient hints to guide students on how to realize the algorithm in Matlab, which gives students a lot of opportunities to understand the theoretical concepts learned in class.

Here are some points that I think could be improved:

Firstly, this course ignores some topics in machine learning which are seen important, such as k-nearest neighbours, naive Bayes, decision trees, random forests. These topics are highly suggested to be taught from my own perspective.

Secondly, the reading notes are missing from the SVM lectures. Since it's an online course for students and many students pay for it, the reading notes should be in high-quality and are not supposed to be missing, which may give students many inconveniences.

Thirdly, I hope there are some supplementary materials for teaching the most prevalent machine learning tool used in the industry such as Scikit-learn.

Fourthly, I hope the course can add a capstone project for students to apply what they have learned in class and show what they have done to future employees, which will be an effective way to have a kick-start in machine learning industry.

Overall, even though it's not a perfect course, it's a really excellent course for having a start in the machine learning field. And I really wish this course can be better and inspire the interest for every student who has a passion for machine learning and data science.

von Rakshith B

Oct 06, 2019

This is a great course. Dives in to a mathematical concepts behind machine learning algorithms and explains them in easy to understand steps.

von Feerong N

Oct 06, 2019

知识的安排很合理,方法也都容易掌握,可惜没有直接对第一周的简介中的应用的实现。

von MOHAMMED R D S

Oct 07, 2019

This is my awesome experience in my life i hope i could able to make better improvement myself and learn lot of things in future like that

thanks !!!!!

von Chandrasekhar K

Oct 08, 2019

Quite Informative

von Anurag A

Oct 05, 2019

The course overall was very good except the errors in programming exercises

von Mathis V E

Oct 06, 2019

It's a good course, but its kind of old and dated already.

von Aayan M

Oct 07, 2019

A MUST DO COURSE IF YOU WANT TO GET IN THE WORLD OF MACHINE LEARNING:

PROS:

1)WILL PROVIDE DEEP KNOWLEDGE OF ALGORITHMS

2)SMALL ASSIGNMENTS IN BETWEEN MAKE YOU REMEMBER THE THINGS YOU LEARNT IN VIDEOS

3)GIVES A FULL OVERVIEW OF MACHINE LEARNING WORLD TO A NEWBIE.

CONS:

1)ALL OF THE CODE IS PRACTICED IN OCTAVE WHICH IS NOT USED IN INDUSTRY MUCH.

2)ASSIGNMENTS ARE PRETTY TOUGH SOMETIMES.

FINAL WORDS:

GO FOR THE COURSE, YOU WON'T REGRET.

AND WELCOME TO THE MACHINE LEARNING WORLD.

von Keyrellous A

Oct 26, 2019

the course was amazing. Yet, I didn't like coding in OCTAV

von siyaram v

Oct 26, 2019

should focus on course content guidelines, there are error in formula in the course.

von Soumik B

Oct 26, 2019

Nice

von Kim, S

Oct 26, 2019

You can start it easily. It requires you only basic knowledge of linear algebra, so it won't make you hesitate to study.

On the other hand, it would be much better if it offered more complicated examples for practice or more detailed explanations of models like motivation of using them or what is happening under it.

Still it was really great lecture since it offers very well designed exercises and good explanations.

von Mohibullah S

Oct 29, 2019

While the course focuses on implementation of ML algorithms and their implementation, it would be very nice to have an explanation of the underlying mathematical concepts for these methods.

Also, it would be nice to have a big project, or a project that is done in stages as the weeks progress, towards a bigger real life application like the Photo OCR

von Kathleen R

Oct 28, 2019

Good course. I wish there was a bit more derivation/depth but it exceeded my expectations and I learned a lot.

von Sean C

Oct 26, 2019

Mentors were excellent. Tutorials for programming assignments were excellent. Videos were very good. PDFs with the programming assignments were sometimes behind the times, too many unresolved errata.

von Umair A

Oct 27, 2019

This course goes so much depth into the fundamentals of Machine Learning and its concepts. It is very useful to get deep understanding of the concepts. But, I will suggest making a few improvements in this course as it is too old and audio qualities are very low. and also, having some Python-based implementation will lead some industry-friendly applications

von John H

Oct 27, 2019

Excellent curriculum. struggled with quiz wording; on many occasions, I simply did not understand the question as worded. Octave on OS X fiddly... The "pause" primitive in the MacPorts version of Octave didn't work and it was necessary to write an override;

The UX "course flow" of the Coursera material is inconsistent. For example, moving on from quizes requires a different navigation pattern than the rest of the course.

The exercise environment is good and the exercises are excellent; nonetheless, a large amount of preprocessing and "heavy infrastructure lifting" is done for the student. While I understand the practical considerations regarding avoiding distracting obstacles in order to focus on the core concepts; a collateral result is many students could vastly under appreciate how much preprocessing has been done on their behalf and take this for granted. Perhaps the student should be advised to understand how much preprocessing was done and how they need to understand the scope and effort involved; at least so they know to include budget and resources for this kind of Data Prep wok that ay be required;