Chevron Left
Voltar para Aprendizagem Automática

Comentários e feedback de alunos de Aprendizagem Automática da instituição Universidade de Stanford

4.9
estrelas
163,453 classificações
41,933 avaliações

Sobre o curso

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....

Melhores avaliações

AB
30 de Ago de 2020

A brilliant sequence of topics and fundamentals to get a stronghold on ML . The learnings I obtained from this course will always be my guiding factor in working through the projects in my life ahead.

YN
18 de Jul de 2021

Amazing really felt that I learnt something substantial. Very happy that I chose this course over others Andrew Ng Sir explained everything very clearly to a required level of depth.\n\nThank you Sir!

Filtrar por:

301 — 325 de 10,000 Avaliações para o Aprendizagem Automática

por Nazir A Z

29 de Jul de 2021

great

por Lichen N

28 de Ago de 2019

深入浅出

por Sam C

2 de Jan de 2020

I'm not crazy about online learning. There are certain aspects of classroom learning that online learning can't give. But as far as online learning goes, this course is probably about as good as it ever gets.

Prof. Ng gives very clear expositions of the fundamentals of machine learning. Anyone taking this class and completing the assignments will be ready to apply machine learning to at least some simpler real world problems and should be in a position to quickly pick up more advanced techniques for more complex problems.

The exams are fair (although I think some more work could have been done to make many of the questions less ambiguous). The programming assignments can be a time sink, but I don't think they could have been any shorter and still give valuable practice in using the techniques outlined in the lectures.

Students who already have a background in linear algebra or the basics of data analysis might find the pace of the class in the early units, where Prof. Ng deals with linear regression, to be rather slow. But if you can get through those early units, you will definitely find yourself dealing with new material (and occasionally appreciating the initial slow pace).

Octave/Matlab is the only language in which the assignments are accepted. I personally would have voted for python. But Prof. Ng spends a few lectures telling you all you need to know about Octave/Matlab, for the purposes of the course. (To save time, I would advise that you spend a day or two learning the language on your own before starting this course. That will allow you to stay that much more ahead of the due dates. But maybe that's just me.)

One word of warning is that, as a friend of mine said after taking a machine learning class in a traditional university classroom, this material makes machine learning accessible, but also takes the "magic" out of it. If you are impressed at how Netflix can be so good at recommending new movies for you to watch, well, after taking this class, you won't be impressed anymore. You'll probably be figuring that, yeah, they probably have some tricks I don't know about, but I could do 90% of what they're doing myself! Which actually means it's a good class!

One thing I definitely would have added are some words at the end of the course about what the "hot topics" are in machine learning, and suggestions about where to go from here, what topics would reward further study, and what books, websites etc. are available for studying them. For example, some words on where to study how and when machine learning turns into full blown artificial intelligence would be appreciated.

The only real gripe I have is that the assignment due dates really didn't give appropriate regard to how busy real life can get during the winter holidays. After all, the big selling point of online learning is flexibility! Right?

In summary: I figure this class is about as good as online learning will get. The instructor is very clear; the assignments are fair and useful. I would have done a few things differently, but nothing is ever perfect. This is a good class for anyone wanting to know the basics of machine learning. Four stars.

por Saideep G

9 de Abr de 2019

Very well made, well paced. Better than majority of college courses. Some errors do pop up midway through the course that should be addressed. It can be frustrating to push through these issues sometimes but they are the only thing keeping from 5 stars.

por Doreen B

9 de Jun de 2019

Well explained, at the end of this course you will understand the subject and hold coherent conversations about it. Matlab implementation relatively simple, maybe too much so. Highly recommended course.

por Moto G

8 de Nov de 2018

There is a lot to say about you Andrew sir but in few words - "Thank you very much for teaching us the ML concepts in such a beautiful manner "

por Mehdi E F

19 de Mar de 2019

Very instructive course.

Thank you.

It would have been great to get an OCR exercice at the end.

por Nils W

23 de Mar de 2019

Great course, but the sound quality is quite bad.

por Sai V P

5 de Ago de 2019

Better upgrade from matlab to Python

por Alexander S

17 de Jul de 2018

I think the rating depends on the expectations.

For a beginner with no prior background with Linear Algebra, statistics, Matlab etc, this is a good overview course (4 stars).

For a professional with prior background, I think this is a poor course (2 stars), because it fails to meet the expectation of learning a deeper understanding of the subject.

The materials covered were with low academic quality (suited for beginner students), any derivations or proofs are omitted if they are non-trivial. The theoretical background created is shallow. I didn't really get a good understanding of the fundamental tools and algorithms used in practical ML solutions, except for the simplest ones.

Yes, the course did give me some better background in ML. But the statement of Mr Ng that the course graduates are now ML experts is highly questionable.

In addition, there is a significant errata for part of the videos & slides - it would be nice to correct them. The fact that about a half of the course material has only slides (which are not always self-explanatory) and not structured course notes is also a point that I recommend improving.

por Stefano B

10 de Set de 2016

Despite I guess the course has a pretty good coverage of the ML basics, it is definitely just an introductive class. In particular I was surprised by the low quality of the material.

The following are my notes and suggestions:

-- I found the lectures highly redundant, with many unnecessary repetitions

-- using a vector notation (like an arrow or a simple line on top of the letters) throughout the course would have make formulas much more readable

-- too much hand writing on the slides while talking: a better set of slides with blocks of text shown at the right moment would be much smoother and readable

-- very, very poor video editing (many times it's clear some parts of the videos were meant to be cut!!)

-- the desire to create a format suitable for people with a scarce algebra preparation lead to use not the appropriate terminology, which would be more correct and easier to understand. Just realize that ML is basically applied math, and without a good math knowledge it is almost pointless to approach the subject

por Eric S

6 de Jun de 2018

This course needs to be severely updated and fixed. It is mostly kept alive by the amazing community of mentors, in particular, Tom Mosher. Without Tom, I would have gotten extremely frustrated with the weird quirks that come about during assignments. One important piece of advice: if you can do assignments in an Octave environment such as GNU Octave 4.0.3, I'd strongly recommend it (Althought it tends to crash ofter, so save, save, save!!!).

por Vyacheslav G

23 de Fev de 2019

Sadly it's just introduction. And i would recommend to make course for python instead of matlab/octave

por Malcomb M

21 de Jul de 2017

Content was OK, but quality of teaching was fair at best -- important points glossed over, many not made clear at all, some simply omitted: Bayes classifiers, decision trees, etc, etc.. Audio visual quality of lectures poor. Ng's onscreen scrawls and voice recording were terrible, and there were many mistakes in graphics. Numerous typographical errors in exercise instruction .pdf's. Exercise text itself (ex__.m files) had numerous "pauses" that failed to instruct the user what he had to do (or not do) next, so you had to carefully examine what followed. If more care was put into exercise construction, the "pause" text in the command window would not just say "Enter to continue" but say what coding action was needed to continue. Obviously a lot of work has already been done on interactivity: Quizzes, online Submit scripts, which for me all worked extremely well. But clearly the course could use a lot of improvement in many aspects. Thus I grade it: C-

por Matthew C

31 de Mai de 2019

Dr. Yang does an excellent job explaining concepts and showing the detailed mechanics of any example he brings up. This being said, I felt the course offered more of an overview, and for anyone with a college statistics and programming course, this won't be very useful, frankly. The course didn't provide lots of new information, and I think much of the actual theory and implementation for ML and its applications would be better broken up into a series of more rigorous courses. This would however, be a good fit for someone working in management who needs a quick understanding of the most basic principles of ML.

por Ranjit B

24 de Dez de 2020

While the contents are good and the teaching pace is just right, I am deeply disappointed by the lethargy of Coursera in not fixing trivial errors in its assessment tests. Answers for even some trivial questions are graded as incorrect. Those result in incorrect grading and a frustration. When I am paying to get the assessments and a completion certificate, this is just NOT acceptable!

por Andrea A

27 de Out de 2019

you have to teach this course with Python otherwise Octave is purely a waste of time. You need to keep up with time. Nobody in the financial industry uses Octave. Also, you need to show way more examples and exercises to allow students to absorb theoretical concepts.

por Deleted A

13 de Jun de 2020

Sound clarity is so poor sometime the volume is very low and some point it too hight, how can we concentrate on the course. Online course are stand on two main pillar video and audio, video s good but audio 2/5.

por Anton

11 de Mai de 2018

Material of this course could be presented much deeper. Mr. Ng tries to avoid mathematical explanations.

por Timothy B

18 de Jul de 2020

Out of date, and video quality bad enough to be distracting

por Loftur e

17 de Set de 2018

Assignments are very messy.

por pat

15 de Fev de 2021

I'm glad I didn't pay for this one. The answers in the quizzes are not correct. I checked them. Also, they don't tell you until week 2 that you will not be able to use any strings in your files in Matlab and Octave, everything has to be a number. I'm not sure this is useful to anyone. Bec the answers are wrong in the tests you won't be able to pass any of the quizzes, I got 60% on them. I retook each of them 6 times. I even checked the answers on Octave. Whoever wrote the quizzes did a poor job. I also did not understand any of the homework labs. I tried doing them and there were no instructions and the scripts did not work. Unfortunately, I can't recommend this class. It looks like the person who did the videos spent a long time on them, but whoever wrote the quizzes and homework did not check anything. Really sad. They could have made some money off of this one. Just sloppy.

por Maarten d s

7 de Jan de 2020

the quizzes were very good but the programming tests were badly made and not well enough explained.

some problems can come from having Dutch as first language others from the continuous task of just translating the formula given into a formula for the programming. or just plain old copy paste from the instructions of the file itself

por Miguel C C

6 de Jul de 2020

Lioso y muy mal organizado. Las preguntas de los test hacen referencia a otros temas y la puntuación es injusta. En general, muy decepcionado y voy a pedir la devolución del dinero.

por Gosforth

10 de Jul de 2019

My feeling is that the author of this course has no idea what is "Machine learning" - I have the impression that he repeats slogans which he does not understand.