Mathematics for Machine Learning: Multivariate Calculus に戻る

4.7

1,911件の評価

•

287件のレビュー

This course offers a brief introduction to the multivariate calculus required to build many common machine learning techniques. We start at the very beginning with a refresher on the “rise over run” formulation of a slope, before converting this to the formal definition of the gradient of a function. We then start to build up a set of tools for making calculus easier and faster. Next, we learn how to calculate vectors that point up hill on multidimensional surfaces and even put this into action using an interactive game. We take a look at how we can use calculus to build approximations to functions, as well as helping us to quantify how accurate we should expect those approximations to be. We also spend some time talking about where calculus comes up in the training of neural networks, before finally showing you how it is applied in linear regression models. This course is intended to offer an intuitive understanding of calculus, as well as the language necessary to look concepts up yourselves when you get stuck. Hopefully, without going into too much detail, you’ll still come away with the confidence to dive into some more focused machine learning courses in future....

Nov 26, 2018

Great course to develop some understanding and intuition about the basic concepts used in optimization. Last 2 weeks were a bit on a lower level of quality then the rest in my opinion but still great.

Nov 13, 2018

Excellent course. I completed this course with no prior knowledge of multivariate calculus and was successful nonetheless. It was challenging and extremely interesting, informative, and well designed.

フィルター：

by Olena K

•May 21, 2018

Not enough detail in the explanations and little to no instructor participation in the forums.

by Arnaud J

•May 23, 2018

The course is still a bit young, some errors appear here and there sometimes, and some parts of it are a bit steep.

Otherwise, this is a good course, focused on derivatives.

by mrinal

•Jun 07, 2018

i think some of concepts touched the surface and it was difficult to get a deep understanding .Probably the course could have provided some external links for those topics where people could read .

by Ronny A

•Jun 27, 2018

Course is pretty good. I like how well thought out the assignments are and the use of visualizations, even in the assignments, to enrich intuitive understanding. There were a couple of instances where the content wasn't clear and I referenced Khan Academy to clarify things for myself. The reason I give this course a 4-start rather than a 5-star is that it seems the teachers or else TAs were not responsive. Specifically, myself and another person had posted in the discussion forum how it seemed one of the slides had a typo in the Jacobian contour plot. There was no official response to this.

by Xiao F

•Apr 23, 2018

the basic concepts are explained clearly, but the step of the lecture became more fast than the course of linear algebra. More detail proof and application of theory is expected.

by Rinat T

•Aug 01, 2018

the part about neural networks needs improvement (some more examples of simple networks, the explanation of the emergence of the sigmoid function). exercises on partial derivatives need to be focused more on various aspects of partial differentiation rather than on taking partial derivatives of some complicated functions. I felt like there was too much of the latter which is not very efficient because the idea of partial differentiation is easy to master but not always its applications. just taking partial derivatives of some sophisticated functions (be it for the sake of Jacobian or Hessian calculation) turns into just doing lots of algebra the idea behind which has been long understood. so while some currently existing exercises on partial differentiation, Jacobian and Hessian should be retained, about 50 percent or so of them should be replaced with exercises which are not heavy on algebra but rather demonstrate different ways and/or applications in which partial differentiation is used. otherwise all good.

by Daniel P

•Aug 22, 2018

Interestin to refresh notions you already learned. Probably a bit difficult if you're totally new to multivariate calculus

by Matt P

•Jul 19, 2018

Great class - very informative and eye opening - even with quite a bit of linear algebra background. Really liked the eigenvector and eigenvalue section - great descriptions. I wish the neural network discussion went on a bit further. I found some of the programming assignments' instructions a bit vague and confusing - what should have taken a few minutes ends up taking a half hour.

by Philip A

•May 16, 2019

Excellent Instruction

by Harsh D

•Jun 03, 2019

Awesome course, just wish it had more info on hessian.

by Surinder D

•Jun 10, 2019

1.Week 5 should be taken in separate module dedicated to statistics.

2.The duration of course can be increased.

3. Week 3 and week 4 can be made more detailed

by Chika

•Jul 09, 2019

Feedback on assessment could be improved, and there could be more practice questions relevant to the final assessments

by Fang Z

•Jul 11, 2019

I really love Samuel's teaching style. He strived to make people understood by showing a lot of graph and I can easily follow him step by step. However, David's teaching I couldn't follow up his mind much maybe because less explanations given during the lecture.

In addition, I found some quiz have huge amount of calculated amount which I really spent a lot time to verify the answer.

Finally, I hope more detailed explanations could be given if I made mistakes in some quiz so I could boost what I've learned so far.

Thanks,

Fang

by Eric G

•Jul 17, 2019

A brief but also very in-depth course

by Clayton

•Jul 22, 2019

teachers are awesome but the last notebook needs a little work i believe.

by Ashish k

•Jul 28, 2019

Superb quality. The way instructors teach is really innovative. The course is good in terms of the area it covers but lacks depth, but is a good starting point if you want to dwell more in detail.

by João M G

•Jul 31, 2019

Weeks 1-4 are great! Weeks 5 and 6 are longer and less explanatory.

by Viacheslav P

•Aug 23, 2019

Good course, but some things seem to be not well discussed and explained, I had to refer to another resources to understand what's going on.

by Prof(Dr) S R

•Aug 25, 2019

nice

by Valentinos P

•Aug 25, 2019

A very nice course that builds your intuition in Multivariate Calculus and also introduces you to some basic consepts in machine learning.

by Davide F

•Sep 12, 2019

Some complex topics were explained a bit too fast. The course on Linear Algebra was better.

by Alfred S

•Jan 13, 2019

Course would be prefect if there would not be technical issues with opening notebooks. It slows me down by 1 week. But content was really relevant to ML.

by Maksim U

•Jan 03, 2019

I did learn quite a lot throughout the course. The problem is that most of my knowledge came from elsewhere while the explanations by the course instructors were quite unclear till I referred to extra resources. At the same time, some other explanations were on the obvious side, so I'd say the instructions are kind of inconsistent in their difficulty. The real-life examples were relly good though. The same concerns the quizzes, some are absolutely great and intuitive, while the others just leave you puzzled about what you are even expected to do with no extra info offered when failed.

The course is kind of sloppier than the first one and the reviews say the third one is even worse, so I won't be doing it.

Finally, I cannot even complete the last graded assignment and get my certificate as well as some other learners because the thing just throws an error all the time. There is zero reaction from the crew that is supposed to be moderating the forums.

All in all, a fine "guideline" course. But do not expect to be presented much inside the course itself.

by Rishabh J

•Mar 08, 2019

Not very challenging

by Aviv P

•Dec 06, 2018

many topic were explained badly