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:

25826 - 25850 von 27,242 Bewertungen für Maschinelles Lernen

von Shakir A

Jan 03, 2017

very nice course which explains the basic theoretical concepts and implementation ideas

von Aashik J

Sep 05, 2017

It's a bit outdated now, I think. Plus, his lectures that are available in YouTube are way more challenging/fascinating. Looking forward to his latest AI course though.

Nothing can take away the fact that he is an amazing teacher.

von nobita

Apr 26, 2016

A great, succinct course is for begin learner.

von HanByul Y

Apr 17, 2016

This course is very kind and easy to learn.

von Petr L

Aug 06, 2017

Solid foundational knowledge for those starting in ML. I like the structure of the class overall, building up on content of previous section, and the choice of MatLab as the the language/programming environment. I'd wish there was more time spent on mathematical aspects (e.g. for PCA or backprop), but I do understand that's probably unrealistic for an online class, and the additional theory could be gained elsewhere. Good practical advice on optimizing and tuning the ML systems (e.g. week 6), though appreciating this knowledge probably takes more practical applications. Finally, I found the quiz sections in Week10/Week11 to be more cursory compared to the other weeks, and wish there were practical assignments in the last two sections.

von Ricardo P

Apr 25, 2018

I like the way Andrew explains and highlight important details for the real world.

von Abhimanyu C

May 04, 2017

Course only gives an overview.

von Ivan R P

Sep 29, 2015

Wonderful course! Sound quality requires revision, but content is supreme.

von Joe K

Feb 06, 2016

Great! This is a great course to learn the idea of machine learning even I am not a computer science and data science student. It provides a chance for us to study different type of machine learning algorithm. The assignment also gives you a chance to practice these algorithms on some application example. If this course can provide more deeply mathematics algorithm or guideline for future study on learning algorithm, it will be a perfect course!

von Stephen M

Oct 04, 2015

Video lessons are excellent. Homework is well-written and does a good job of illustrating the lessons.

von Salim T

Mar 28, 2016

Pros:

1. Good examples and way of discussion.

2. Real experience in using of real applications.

Cons:

1. Usage of MATLAB ( why not R or Python?)

von S.Elango

Oct 24, 2016

This Machine Language course is well structured and easy to learn for students who have basic knowledge of matrix and programming.

von Todd L

Apr 02, 2016

The lectures were good to excellent. The homework assignments were decent but felt a little "dumbed down". If it had been based on Python or R instead of MATLAB/Octave it would have been better though.

There were lots of problems with submission using Octave. I almost quit because I just couldn't get it to work correctly, at least on a Mac. Switching to MATLAB made it easier. But MATLAB isn't something I'm going to be able to freely use after the course.

Overall I found it to be a nice basic introduction to Machine Learning. It seems to have really just scratched the surface in terms of depth, but the breadth was good. I would recommend it to anyone looking for an introduction or first course in machine learning.

von Sourabh S

Aug 16, 2015

The course content is thorough and meticulous. One of the best course I've pursued.

von Kallol K D

Sep 26, 2015

Great course

von Matthew B

Aug 09, 2016

Great material, great instructor. The use of Octave was unfortunate, though; I regularly had problems with it crashing.

von Jacob R

Sep 01, 2017

A very good course and introduction to this topic overall. The videos are perhaps a bit old and some of the material might benefit from being updated, but this is still a solid class and was very much worth my time. It has left me interested in pursuing this topic further, and possibly consider it as a career choice sometime in the future.

The programming exercises were useful for learning the material and not too difficult or time consuming, and generally the help available on the class forums was enough to get me through the few difficult parts (learning how to properly vectorize some of the problems can be difficult trying to do it on your own based only on the lectures).

von Hachem

Sep 17, 2017

Very nice course, thaught by one of the leaders of the field. Very practical but not enough theoretical and clearly designed for people with not that much of mathematical background (if at all) or from a software engineering/computer science background, which is frustrating sometimes when it comes to understand the underlying theory about some of the more complex learning algorithms (SVM, kernels, backpropagation algorithm). Good experience overall, i'd recommend for a very good introduction to the vast world of machine learning.

von Mantas

Apr 10, 2018

I wish programming with python was allowed for exercises.

von Carmine L

Aug 17, 2016

Very well as introduction and more to the matter.

von Arnau P

Feb 11, 2018

An easy way in to a steep learning curve. The exercises are cool but could be more involved.

von Ankur R

Apr 30, 2018

great one

von Kartik S

Jun 22, 2017

Very very good introduction to machine learning. Don't have anything bad to say except for one thing that the assignments were too easy but I am guessing that's how it is for online courses. Thank you, Andrew.

von GOURAB G

Dec 06, 2015

Great course but light on the mathematical part would love to get those insights.

von Tejas S N

Feb 11, 2017

Amazing Course, teaches you right from basics. Prof. Ng explains everything in a manner which makes it easy to understand. Only one shortcoming I found in this course is, not challenging enough programming exercises. I understand that course has to cater a general and large crowd, but adding maybe a few optional challenging exercises might help. Also, if optional video content is provided for algorithms which have been taught in CS229 but are absent here, it will be really useful.