Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Google's Free Deep Learning Course

udacity.com

Post reply on HN
Print view View original

21–30 of 66 posts

Re: Google's Free Deep Learning Course

#21

Post by stared »

magicmu wrote: post #17

How accessible is a course like this with no prior knowledge of linear algebra? I know it's listed in the pre-reqs, but with a good head for math and lots of calc, is it something that could be picked up along the way? I'm normally pretty bold about stuff like that, but I know it's a core part of deep learning / ML. If it's really necessary, if anyone has any resources for linear algebra run-throughs it would be grea…

Linear algebra is simple (but ubiquitous - so you need to feel it, not only "sort of follow it").

Some visual matrix operations are here: http://setosa.io/ev/ If you want a beginner textbook, I recommend http://www.matrixanalysis.com/

Again, it is simple, so maybe you can even take course and look up Wikipedia when needed (but for me it is hard to guess you level, current knowledge, etc).

In any case, this ML course assumes some ML knowledge.

Re: Google's Free Deep Learning Course

#22

Post by vowelless »

stared wrote: post #21
magicmu wrote: post #17

How accessible is a course like this with no prior knowledge of linear algebra? I know it's listed in the pre-reqs, but with a good head for math and lots of calc, is it something that could be picked up along the way? I'm normally pretty bold about stuff like that, but I know it's a core part of deep learning / ML. If it's really necessary, if anyone has any resources for linear algebra run-throughs it would be grea…

Linear algebra is simple (but ubiquitous - so you need to feel it, not only "sort of follow it"). Some visual matrix operations are here: http://setosa.io/ev/ If you want a beginner textbook, I recommend http://www.matrixanalysis.com/ Again, it is simple, so maybe you can even take course and look up Wikipedia when needed (but for me it is hard to guess you level, current knowledge, etc). In any case, this ML course…

I like this writeup: http://betterexplained.com/articles/linear-algebra-guide/

Re: Google's Free Deep Learning Course

#23

Post by magicmu »

jskonhovd wrote: post #20
magicmu wrote: post #17

How accessible is a course like this with no prior knowledge of linear algebra? I know it's listed in the pre-reqs, but with a good head for math and lots of calc, is it something that could be picked up along the way? I'm normally pretty bold about stuff like that, but I know it's a core part of deep learning / ML. If it's really necessary, if anyone has any resources for linear algebra run-throughs it would be grea…

I would start with the nano degree program if you don't have any prior knowledge of ML. Udacity has a Linear Algebra review course, but I don't believe it is public for now. I had taken a linear algebra course before I took the GT ML class, but I wasn't a expert by any means. I don't believe you will need a deep understanding of linear algebra before taking this class. Singular value decomposition might come up. I th…

Awesome, thanks for the pdf!

Re: Google's Free Deep Learning Course

#24

Post by magicmu »

stared wrote: post #21
magicmu wrote: post #17

How accessible is a course like this with no prior knowledge of linear algebra? I know it's listed in the pre-reqs, but with a good head for math and lots of calc, is it something that could be picked up along the way? I'm normally pretty bold about stuff like that, but I know it's a core part of deep learning / ML. If it's really necessary, if anyone has any resources for linear algebra run-throughs it would be grea…

Linear algebra is simple (but ubiquitous - so you need to feel it, not only "sort of follow it"). Some visual matrix operations are here: http://setosa.io/ev/ If you want a beginner textbook, I recommend http://www.matrixanalysis.com/ Again, it is simple, so maybe you can even take course and look up Wikipedia when needed (but for me it is hard to guess you level, current knowledge, etc). In any case, this ML course…

Yeah, your last suggestion was what I was leaning towards. Because of the ubiquity of linear algebra, though, this seems like as good a time as any to start getting a good handle on it. Thanks for the resources!

Re: Google's Free Deep Learning Course

#25

Post by alexott »

it_learnses wrote: post #12

Would it be beneficial for me as a developer to take these machine learning courses? I took a course in the uni a while back and know the general techniques, but I'm not sure how it would help me in my career unless I'm doing some cutting edge work in the field or focusing on a machine learning career, in which case wouldn't I need to be pursuing a postdoc or something in it?

It's enough tasks where you need to have understanding of the ML algorithms/workflows/tools, and be able to implement production system that integrates them into real systems, generating value for companies. In many cases you need to have very good domain knowledge & software development skills in addition to understanding of ML. And in ML-related systems, the big part of implementation not ML itself, but a lot of supporting stuff (figure 1 from "Hidden Technical Debt in Machine Learning Systems" paper (https://papers.nips.cc/paper/5656-hidden-technical-debt-in-m...) quite useful for understanding).

I personally took several ML courses from coursera/udacity/edX, and they helped me when I decided to move to another group that works on the ML-related projects.

Re: Google's Free Deep Learning Course

#26

Post by jokoon »

ganeshkrishnan wrote: post #4

I think intro to machine learning https://www.udacity.com/courses/ud120 is the prerequisite to this course

I was just beginning to give it a try, it just requires you to type the code that is shown on video. Poor way of teaching something, it seems at first. I sense this course is just to teach me the tools of the trade, not really enabling students to fully understand what they're doing.

On the other hand, some months ago I watched the ML course by Andrew Ng, and I still did not understand how to test a simple linear regression for myself, so I did not really understand it, and stopped watching the course.

Re: Google's Free Deep Learning Course

#27

Post by rahimnathwani »

jokoon wrote: post #26
ganeshkrishnan wrote: post #4

I think intro to machine learning https://www.udacity.com/courses/ud120 is the prerequisite to this course

I was just beginning to give it a try, it just requires you to type the code that is shown on video. Poor way of teaching something, it seems at first. I sense this course is just to teach me the tools of the trade, not really enabling students to fully understand what they're doing. On the other hand, some months ago I watched the ML course by Andrew Ng, and I still did not understand how to test a simple linear reg…

You might like the book 'data science from scratch' by Joel Grus. He uses Python without ML libraries and explains clearly what's going on.

Re: Google's Free Deep Learning Course

#28

Post by j_s »

rahimnathwani wrote: post #27
jokoon wrote: post #26

Earlier quoted context omitted.

I was just beginning to give it a try, it just requires you to type the code that is shown on video. Poor way of teaching something, it seems at first. I sense this course is just to teach me the tools of the trade, not really enabling students to fully understand what they're doing. On the other hand, some months ago I watched the ML course by Andrew Ng, and I still did not understand how to test a simple linear reg…

You might like the book 'data science from scratch' by Joel Grus. He uses Python without ML libraries and explains clearly what's going on.

http://amzn.com/B00W4DTP2A

Re: Google's Free Deep Learning Course

#29

Post by wrsh07 »

jokoon wrote: post #26
ganeshkrishnan wrote: post #4

I think intro to machine learning https://www.udacity.com/courses/ud120 is the prerequisite to this course

I was just beginning to give it a try, it just requires you to type the code that is shown on video. Poor way of teaching something, it seems at first. I sense this course is just to teach me the tools of the trade, not really enabling students to fully understand what they're doing. On the other hand, some months ago I watched the ML course by Andrew Ng, and I still did not understand how to test a simple linear reg…

From the yc reading list 2015 [http://themacro.com/articles/2015/12/yc-2015-reading-list/], they recommend [for Neural Networks] this book: http://neuralnetworksanddeeplearning.com/

It's more about understanding than "learning tools."

Post reply on HN