Chevron Left
Retour à Apprentissage automatique

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

4.9
121,373 notes
29,802 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

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.

PM

Jul 14, 2019

This course is amazing and covers most of the ML algorithms. I really liked that this course has emphasized math behind each technique which helps to choose the best algorithm while solving a problem.

Filtrer par :

28351 - 28375 sur 28,918 Examens pour Apprentissage automatique

par Hujun Q

Jun 27, 2019

Nice for the beginners to quickly get basic ML knowledges, but not good for the medium or advanced level learners who want to go deeper into theories.

par Ihar B

Jun 28, 2019

Very Good, but I wish it would be more end to end

par Hidetsugu T

Jun 28, 2019

Prof Ng explanations and helping the student understand the topics in an intuitive was was very beneficial.

par Satyam s

Jun 28, 2019

I have just completed week 3 and I think study material is good. if some coding example are given to exercise then it would be more easy to learn and grab some extra knowledge. I am feeling that we get very less time to work on coding.

par Avaneesh

Jun 28, 2019

The course was pretty good...

par Hritik M

Jun 29, 2019

It's a very good course for the beginners in the field of machine learning,every topic is explained by well suited examples so the students get an idea about the topic.

par Prabhat D

Jun 30, 2019

Great course. But course material has not been updated since many years. Maybe material should be updated. Also would have preferred Python instead of Octave.

par VInjit R

Jun 29, 2019

I thought ML could give me a heart attack cause of math but the intuitions made it lot easier

par Radu S

Jun 30, 2019

They should really think about switching to Python, as, after trying Octave for this course, I definitely do not recommend it. Otherwise the course is really good, although I found myself questioning some mathematics demonstrations not provided in this course, which I will look for, and also I will be reading a few books to better understand the subject. However, overall it's been a great experience, and it's always easier to understand something when you have an expert like professor Ng teaching you (even virtually).

par Navish G

Jul 02, 2019

A very good course, only problem is that it is not taught in Python

par Savyaraj D

Jul 01, 2019

I loved the hands on implementation provided in this course through the programming exercises. Also, the advice for applying machine learning systems on real problems and their performance evaluation was very helpful. Although a more rigorous analysis of the statistics and linear algebra could have been more satisfying for me, I really enjoyed the course overall.

par Sanjay K

Jul 05, 2019

The machine learning course offered by coursera is a very useful one for the beginners. Learnt a lot from this course

par Atakan S B

Jul 05, 2019

Sometimes the assignments are ambigious. Other than that the course is just fine

par Alaedine B

Jul 05, 2019

Absolutely amazing. Well balanced between theory and application.

Would be great if Python was used instead of Octav.

par oumaima b

Jul 04, 2019

A good and interactive leson that explains in a simple way.

thank you so much for it

par Mehrdad P

Jul 04, 2019

helps you get familiar with the basic concepts of machine learning, but not for in-depth discussion.

par Prakarsh G

Jul 06, 2019

Love the course so far! However, the instructor is inaudible at certain points.

par Mark C

Jul 05, 2019

Some complicated topics very well explained

par Akshit A

Jul 06, 2019

An amazing course for a beginner as well as a person with intermediate skills in the field. The exercises are a must do, and are even more intutive than the lectures, would have been great to see the implementations in a language like Python/ Ruby, otherwise the course is wonderful to get a firm grip over the mathematical portions of ML and generating a very important intution behind the Algorithm. Kudos to Andrew Ng for providing such a valuable asset!

par Mohamed M L

Jul 07, 2019

A good course so far , it introduces alot the theory about the material , and gives alot of advices on how and when to apply different algorithms , 4 stars because i think that submitting homeworks should be followed by some sort of explanations or solutions to the problems , even tho homworks are a little bit guided !

par Nidhal B

Jul 08, 2019

excellent course. The only down is that we had to use Matlab for the Programming assignments as now languages like Python are more usable in the Field

par Patrick K

Jul 10, 2019

Very nice introduction to machine learning. It helped me a great deal to understand ML concepts, vocabulary (!), algorithms, and cut a bit through the hype. I really liked the programming parts.

The course is held at a very low mathematical level, so that no huge math background is needed to step in. However, this is sometimes a disadvantage because some ideas would be much more digestable if formulated by means of linear algebra, multivariate calculus etc. Concretely, I found it difficult to follow through the videos on training neural networks via backpropagation since there're formulated in an elementwise fashion (so many sums, indices,...). In vectorized form using the language of matrices & vectors, this turned out too be not difficult at all and more accessible.

par Fredrik C

Jul 10, 2019

would be nice with reading notes for all the videos

par Markus M

Jul 10, 2019

Quality of Material is decreasing towards the end of the lectures

par Himanshu G

Jul 11, 2019

fantastic