Chevron Left
Retour à Apprentissage automatique

Avis et commentaires pour l'étudiant pour Apprentissage automatique par Université de Stanford

4.9
119,577 notes
29,353 avis

À propos du cours

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....

Meilleurs avis

SB

Sep 27, 2018

One of the best course at Coursera, the content are very well versed, assignments and quiz are quite challenging and good, Andrew is one of the best guide we could have in our side.\n\nThanks Coursera

CC

Jun 20, 2018

good course; just 2 suggestions: improve the skew data part (week 6) and furnish the formula to evaluate the number of iteration in the window from image dimension, window dimension and step (week 11)

Filtrer par :

27851 - 27875 sur 28,469 Examens pour Apprentissage automatique

par Ramesh P

Nov 16, 2018

Great course. Covered all necessary theoretical background of Machine Learning. Could have been much better if course is revised using Python language :)

par Priyanshi S

Nov 10, 2018

Overall a very good course when it comes to understanding the concepts , though the fact that the programming assignments use octave and when I go to other platforms they ask for python so another language I gotta get my hands on which may not have as advanced libraries as octave ( as thats the whole point of octave) is a little disappointing when t comes to growing in the field(as a student), the notes/reading sections also vanish halfway through the course which is also a setback, sometimes the absence of maths though makes sense obstructs true understanding for me,.. though the knowledge of the instructor, explanations and the fact that they also gave application advice, programming assignments and not just sheer algorithms is highly appreciated. Overall I'm highly satisfied by the course, it solved my purpose of exploring the realm of machine learning highly satisfactorily.

par Sebastian G

Nov 26, 2018

Very good presentation of all the subjects, exercises were demanding without being frustrating. Slides weren't in LaTeX, but you can't have everything.

par Ravindranath T

Nov 18, 2018

Content of course is very simplified and great content.

par Vaibhav G

Nov 19, 2018

The instructor explained concepts really well. The quizzes and programming assignments are well structured to enhance the understanding of the material. I didn't find corresponding reading material for last few lectures, which would be good to add.

par AMIR K

Nov 21, 2018

Felt this course should use python because machine learning potential with matlab/octave is not that much utilized.

par Ahmed I

Nov 20, 2018

It's a good course, instructor is good and explains well, but it should be in python instead of matlab.

par Aashish D

Nov 11, 2018

covers most of the important topics and gets you ready for the world of machine laearning

par Michael M

Nov 24, 2018

Great course!!! Really enjoyed it and thought it was well taught. The only negative is I felt some topics in the later weeks felt a bit rushed.

par Yohanes H P

Oct 09, 2018

The content helps me to understand ML ..the content is very compact

par Andy

Sep 30, 2018

Very good course but little too complicated without good math background. Definitely will come back after some practice)

par Sourav R

Sep 30, 2018

He is an amazing teacher ! I think this is by far the best Machine Learning tutorial ever seen ! But i think there should have also been a few video lectures on how to code in octave and writing codes for algorithms using octave. That would have made this tutorial a completely perfect tutorial. Students do understand what he teaches really well , but im sure many here lack the practice of using octave.

par Risheek P

Oct 02, 2018

The course is obviously downright fantastic. It serves as a very good introduction to the field of machine learning. But it would have been better if some more algorithms like decision trees, random forests and other forms of regression were also included.

par Charles P

Oct 02, 2018

Semaine 1 : très didactique, et permet de rentrer dans le bain du ML de manière progressive avec des connaissances de base (niveau lycée) en mathématiques

par Mery

Aug 20, 2018

Very useful and interesting class for approaching machine learning. I would add that Andrew Ng is an "ace" in the fields of teaching and pedagogy. The fact that he lets us choose whether to deep dive or not into the underlying mathematics is appreciable. The reason I'm giving 4 stars instead of 5 is because i would have liked to work on some python implementation.

Thank you for teaching us.

par SAI A R N

Sep 01, 2018

It was good but had to read lots of supplementary material

par Faraz F

Aug 18, 2018

complicated concepts has been broken into easy and understandable ,simple concepts. boosts one's confidence when ones you start understanding algorithms gradually. makes you realise that machine learning isn't that difficult afterall.

par Овчинников Г О

Aug 18, 2018

Good, but outdated.

par Amer

Aug 19, 2018

Great course from a true expert. Makes it look easy. If you want to get strong fundamentals in ML you should strongly consider taking this class. I gave it four stars because I think the class needs some updating. Some topics seem missing, such as Random Forests, boosting and bagging, LDA.

par Prateek A

Aug 19, 2018

Andrew have done job well to make it simple and structured. Very good foundation to start an AI journy

par vishal k

Aug 19, 2018

try to help us by making these implementations in python.

par Alexey B

Sep 16, 2018

Course is great as a first introduction to a machine learning world. The basic concepts are explained and demonstrated via interesting examples. In my opinion the only drawback is that in many programming assignments the main focus was made on how to vectorize various calculations using Octave/Matlab, instead of digging in the algorithm itself.

par Harsh K

Sep 02, 2018

Awesome

par Zhaoxue M

Sep 16, 2018

I find this course explained very well. I never learned anything related to this topic before. Sometimes i find that it is really difficult to do the homework for programming. In general, i like this course. I learned a lot, and had a new view about machine learning.

par Etienne A

Oct 04, 2018

Great course ! I would have preferred that prerequisites on linear algebra and calculus be mandatory so as to delve deeper into the mathematics, but I understand the choice to keep the course to a broader audience.