-
Notifications
You must be signed in to change notification settings - Fork 54
New page added for Research Area "Automatic Differentiation" #163
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
New page added for Research Area "Automatic Differentiation" #163
Conversation
- also linked to research page - (SEO Optimized) this will help populate CR website in Google Search results for "Automatic Differentiation" - Descriptions taken from/verified from Presentations/Papers found on CR website. Rephrased for better SEO ranking (no duplication from original content on PDFs/Papers/Presentations)
@davidlange6 Requested changes have been made. |
I think my two meta comments remain -most importantly if we want a page that introduces AD we need a more expert team member to start its content. This can help get the right focus and more fundamental references/resources. |
@vgvassilev Can you please nominate a Subject Matter Expert that can update/re-write this content (as requested by David above)? |
Hi @QuillPusher, I can help with this. |
That would be great @vaithak . Please directly make any changes that seem suitable to you. All the source documents that I've used for this info are linked on the post. P.s., I'm not sure how this works, I've invited you as a collaborator on my fork of the website (branch name is |
the input nodes. For every node, it merges all paths which originated at that node. | ||
It tracks how every node affects one output. Hence, it calculates derivative of a single | ||
output with respect to all inputs simultaneously - the gradient. | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe, we can add some images for forward and reverse mode AD, even the one on the Wikipedia page should be good enough.
Hi @QuillPusher, I have tried to improve the content; this may still need some formatting and grammatical fixes, though. |
Thanks for the changes and the pointers @vaithak , I ran it through a grammar tool and added the mentioned images. @davidlange6 This is ready for your review again 😅 |
@vaithak, is that good to go? |
Yup, looks good to me with your suggested changes. |
34b95fe
to
f394f80
Compare
Thanks, @vgvassilev |
also linked to research page
(SEO Optimized) this will help populate CR website in Google Search results for "Automatic Differentiation"
Descriptions taken from/verified from Presentations/Papers found on CR website. Rephrased for better SEO ranking (no duplication from original content on PDFs/Papers/Presentations)