Is an integral really that hard?
Learn TensorFlow and deep learning, without a Ph.D.
11–20 of 47 posts
Re: Learn TensorFlow and deep learning, without a Ph.D.
#12I spent some time learning the high level concepts first—which I found to be a very useful initial orientation—but recently I've wanted to solidify my foundations and learn the math properly.
I've found the math primer (two sections: "Linear Algebra" and "Probability and Information Theory") in this free book to be excellent so far: http://www.deeplearningbook.org/ It's a little under 50 pages for both sections.
I've seen the basics of linear algebra covered in many different places, and I think this is the most insightful yet concise intro I've come across. I haven't started the probability section yet, so I can't comment on it.
Re: Learn TensorFlow and deep learning, without a Ph.D.
#13There seem to be a few of these "learn deep learning without heavy math" courses popping up, for which I'm profoundly grateful. Have people found any of them to be particularly outstanding? I'd be interested - and I suspect many HN readers would be - to hear recommendations.
Andrew Ng's Machine Learning on Coursera is a good for building some solid foundations in ML in general. Keep in mind it's not limited to Neural Networks. The math is kinda light, you either seek to understand it or trust that it works and focus on the ML principles.
Re: Learn TensorFlow and deep learning, without a Ph.D.
#14There seem to be a few of these "learn deep learning without heavy math" courses popping up, for which I'm profoundly grateful. Have people found any of them to be particularly outstanding? I'd be interested - and I suspect many HN readers would be - to hear recommendations.
Andrew Ng's Machine Learning on Coursera is a good for building some solid foundations in ML in general. Keep in mind it's not limited to Neural Networks. The math is kinda light, you either seek to understand it or trust that it works and focus on the ML principles.
> The math is kinda light, you either seek to understand it or trust that it works and focus on the ML principles.
This is accurate and also why I dropped out pretty quickly.
Re: Learn TensorFlow and deep learning, without a Ph.D.
#15What I'd like is a Learn TensorFlow and deep learning with a mathematics/physics background.
I feel you. Try nando de Freitas's course, I liked it a lot.
Re: Learn TensorFlow and deep learning, without a Ph.D.
#16Is an integral really that hard?
Not if you take it a little bit at a time.
Re: Learn TensorFlow and deep learning, without a Ph.D.
#17I spent some time learning the high level concepts first—which I found to be a very useful initial orientation—but recently I've wanted to solidify my foundations and learn the math properly. I've found the math primer (two sections: "Linear Algebra" and "Probability and Information Theory") in this free book to be excellent so far: http://www.deeplearningbook.org/ It's a little under 50 pages for both sections. I've…
I have been doing the same thing. I've also augmented each section with video lectures from Khan academy or other sources. For instance, their videos on the Jacobian were excellent for getting an intuitive understanding of it [1].
I also search for problems on the topic to help solidify my knowledge. You can almost always find a class that has posted problems for a section with answers.
[1] https://www.khanacademy.org/math/multivariable-calculus/mult...
Re: Learn TensorFlow and deep learning, without a Ph.D.
#18Re: Learn TensorFlow and deep learning, without a Ph.D.
#19What I'd like is a Learn TensorFlow and deep learning with a mathematics/physics background.
Udacity / Google course by Vanhoucke I think is the most popular for learning TensorFlow proper - https://www.udacity.com/course/deep-learning--ud730
Re: Learn TensorFlow and deep learning, without a Ph.D.
#20Any versions of this course planned for R Programmers?