Mathematics for Machine Learning: Multivariate Calculus に戻る

4.7

1,791件の評価

•

267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 刘静怡

•Jan 14, 2019

Thank you! Really nice course!

by James A

•Jan 14, 2019

Amazing!

by Grigoraș V

•Dec 29, 2018

The professors are great! Wish we had part of such enthusiasm all throughout high-school. I bet people would enjoy math a lot more.

by Geoffrey K

•Nov 14, 2018

A most intuitive way of learning calculus. Great course!

by 馬健原

•Dec 16, 2018

Good Course

by Nelson F A

•Mar 22, 2019

Very intense course. However, now that I have moved on to Andrew Ng's ML course, I am so glad I finished it. Understanding the math behind ML makes learning it so much more enjoyable. Before it was like shooting in the dark. My python code wouldn't and ML-concepts would take a lot of time and effort to sink in. Sometimes not at all... This course armed me with the tools to succeed in a career in ML and AI. Looking forward to finishing the specialization!

by Mark C

•Jul 31, 2018

As good as the first class in the Math for ML series. Instruction was interesting. Questions were not too confusing. Clearly a lot of time was spent producing this class. Thank you.

by Bernard P

•Jul 29, 2018

Highly recommend

by Jonathan F

•Jul 29, 2018

Following on from the Linear Algebra course, this is equally excellent. Again, the main enjoyment comes from seeing techniques learnt at school (partial derivatives, Taylor series, Newton-Raphson, etc) actually being used in practice.

by Anas N B

•Aug 04, 2018

It helped me to brush up my calculus knowledge.thanks to the team

by Du L

•Aug 05, 2018

Super Great!!!

Clear illustration on multivariate calculus.

by Artem D

•Aug 10, 2018

I really liked the teachers and everything they prepared for the students.

Lectures are entertaining, not boring.

Assignments are interesting. Especially, i've found very useful the structure of learning: (1) you have a short lecture, (2) you have a small quiz which continue to intriduce you to the topic and in parallel let you to try it on practice - it was really great!

Thank you a lot! I loved this course (as a previous one) so much!

by Nitish K S

•Jul 18, 2018

nice !

by Jitender S V

•Jul 20, 2018

Just as great as first course. :)

by Arihant J

•Jul 19, 2018

Nice course. Ppl with who don't have some experience with the content may find the instruction too sparse. But for someone with a decent background its a fucking fantastic course !

by Arnab C

•Sep 03, 2018

I found this one to be probably one the best courses on neural network if someone is keen to learn the underlying mathematics of it. The content of the course is very concise, enough to cover the most important parts that are required to learn machine learning and just enough depth. The quizzes and assignments are of excellent qualities. Overall, I will highly recommended this course.

by sujit j

•Aug 21, 2018

Got excellent understanding of gradient descent in case when there are multiple stationary point

by Joseph J

•Aug 23, 2018

Excellent Review, Just excellent

by Edward K

•Sep 04, 2018

very nice

by 丁榕

•Sep 05, 2018

Totally like it!!!! Really fundamental and both of the two lecturers have made every important key points quite clear.

by Tash B

•Sep 05, 2018

Although difficult, this course makes sense of what is happening under the hood in training machine learning models. Instructors explain things well and the assignments gave opportunities to practice. I thoroughly enjoyed this course.

by Marcelo f

•Sep 04, 2018

Pretty Awesome!

by Ashish R

•Aug 27, 2018

Excellent Course!

by Mohamed R

•Sep 10, 2018

one of the best courses I have ever had.

thanks to instractors and Imperial College London

thanks so much for that specilization it helped me alot

by Patrick L

•Sep 09, 2018

Fantastic overview/refresher of multivariate calculus, with links to ML / neural nets throughout.