This category is for questions and discussions related to the fast.ai course, Computational Linear Algebra. This blog post introduces the course.
Here is advice on how to ask for help in a way that maximizes the chances someone else will be able to provide a helpful answer.
The primary resource for this course is the free online textbook of Jupyter Notebooks, available on Github. Accompanying the notebooks is a playlist of lecture videos, available on YouTube. If you are ever confused by a lecture or it goes too quickly, check out the beginning of the next video, where we review concepts from the previous lecture, often explaining things from a new perspective or with different illustrations.
Here are a few packages and extensions I’ve used to make the Jupyter Notebooks easier to navigate and read:
Hi Rachel
Would you describe the goal of the course as “anything that could speed up your matrix computations”? I know that the goal of the course “Practical deep learning for coders Part 1” was apparent from the introduction video. Asking this because while going through the reading for many of the things I wasn’t able to understand the maths and I was hoping to know whether this course can help fill that gap or whether I would need to do some other course too.
Because the course is “top-down”, we start working with black boxes and many of the math explanations appear later: for instance, in later lessons we cover matrix-vector multiplication, change of basis, symmetric matrices, and projections.
The course does assume some prior familiarity with linear algebra, so it would be helpful to hear if you find specific topics that you think should be listed as pre-requisites.
When I said "Asking this because while going through the reading for many of the things I wasn’t able to understand the maths " I was referring to the fast ai Part 1 course not this one. Reading it again it was ambiguous. Sorry for that.
I really like the objective of the course as I always find the need for some math supplement to understand deep learning and machine algorithm. The materials for this courses are nice too, but so far I feel it is very hard to follow the lecture videos although I just finished lecture 2.
I hope you will keep going! Lecture 2 went particularly quickly, so in lecture 3 I review and re-explain many of the concepts from a different perspective. Most lectures contain a review of the previous lecture at the beginning, so if you are ever stumped, check out the beginning of the following lecture.