terryum / awesome-deep-learning-papers Goto Github PK
View Code? Open in Web Editor NEWThe most cited deep learning papers
The most cited deep learning papers
I wanted to name, e.g., "Review / Survey" as a subsection title, but if I do that, the link in the table of contents loose the hyperlink. That's why I used ugly "Review Survey" instead of "Review / Survey"
Can somebody solve this issue? Thanks!
Thanks for the great list / repository! But would it be possible to assign more Reviewers to make the updating of the list more regular?
http://neuralnetworksanddeeplearning.com/index.html here is another useful book for beginners.
The actual link:
http://papers.nips.cc/paper/6124-improved-techniques-for-training-gans.pdf
Incredibly points to another, not correlated paper.
The correct arxiv paper link is:
https://arxiv.org/pdf/1606.03498.pdf
Many model promoted by these papers have been implemented on github, will you add these implementation reference to your repository?
awesome program!
I found 3 dead links when running fetch_papers.py.
Here are working links for those 3 papers:
3D convolutional neural networks for human action recognition
https://pdfs.semanticscholar.org/3c86/dfdbdf37060d5adcff6c4d7d453ea5a8b08f.pdf
End-to-end training of deep visuomotor policies
https://arxiv.org/pdf/1504.00702.pdf
Mastering the game of Go with deep neural networks and tree search
https://storage.googleapis.com/deepmind-media/alphago/AlphaGoNaturePaper.pdf
Thanks for the great list / repository!
I believe, [http://arxiv.org/pdf/1411.2738v4.pdf](word2vec Parameter Learning Explained) by Xin Rong should be a part of Paper worth reading section. It has 23 citations and explained the word embedding learning process in an excellent way!
Out of interest, where did you get the numbers for citations? Did you use any mechanism for discovering these papers, or was it purely your own knowledge?
This should really help to keep a track of papers read so far. I would love to fork the repo and keep on checking the boxes in my local fork.
For example: Have a look at this section. People fork this repo and check the boxes as they finish reading each section.
Can you please add more "information scent" to the links? A one sentence summary of the paper would be very helpful. Should make the repo a very interesting read :) Thanks!
The link for this paper is broken.
3D convolutional neural networks for human action recognition (2013), S. Ji et al. broken pdf-link
As somebody knows, I deleted the "key researchers" section because some people complained it's unfair. But, since I think "key research" part is still useful information, I'd like reactive after providing reasonable statistics of them.
Are anyone interested in writing a code for getting the statistics of 100 papers' authors?
Hello.
Deep Reinforcement Learning with Double Q-Learning (2016), H. Hasselt et al. is broken. I found this job there: https://arxiv.org/pdf/1509.06461.pdf .
SSL error while downloading
That way many people could import the list into their library without hassle. The bib file should contain dois and url links to pdf files for open access papers.
On a second thought, it might be best to generate the list from the bib file automatically.
Is there a bibtex library output? This would be very useful paper bibliographies and for uploading to paper-reading/-curation apps.
Hi,
In section Optimization / Training Techniques, there are:
Both papers have the same authors, and they both introduce dropout. However, the papers are 2 years apart and the content is not identical. Was the paper just republished after being edited by Bengio, or is there some story behind this? Is it helpful to have both on the page?
Are IEEE papers discouraged?
Because they are not free to download.
Where is the state of the art YOLO algorithm for object detection?
https://github.com/stevekwon211/Hello-Kaggle
It is a Kaggle Guide Document for someone who is new at Kaggle!
./fetch_papers.py: line 4: $'\nAuthor: doodhwala\nPython3 script to fetch the top 100 papers\n': command not found
./fetch_papers.py: line 8: directory: command not found
./fetch_papers.py: line 9: syntax error near unexpected token (' ./fetch_papers.py: line 9:
if not os.path.exists(directory):'
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.