Skip to content
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

Visualizated explanations of the examples #250

Open
johnny5550822 opened this issue May 12, 2016 · 4 comments
Open

Visualizated explanations of the examples #250

johnny5550822 opened this issue May 12, 2016 · 4 comments

Comments

@johnny5550822
Copy link

johnny5550822 commented May 12, 2016

I found the examples founder is great. Have you have any plan to further develop visual explanation on every example file? For example the "recurrent-time-series.lua", when we go over the code, explanation + figures may help the user to understand not only how rnn package works, but also the basic of the recurrent network structure?

@nicholas-leonard

@nicholas-leonard
Copy link
Member

@johnny5550822 Yeah that kind of tutorial would be awesome. Its just that I have been a little overwhelmed with other stuff. Tutorials take time to do. Would you be open to writing one?

Otherwise, I am working on a blog post / tutorial for the noise-contrastive-estimate.lua example.

@rracinskij
Copy link

Trying to understand is that kind of stuff is compatible with rnn's - http://homes.cs.washington.edu/~marcotcr/blog/lime/
If yes, it could eventually add some valuable insights to the rnn mechanics at some later point.

@johnny5550822
Copy link
Author

@nicholas-leonard Yes, I am thinking about it. If I make one for some examples, I will send you the link. A tutorial will boost the good codes of RNN.

@rracinskij Thanks. Yes, I agree with it. Sometime, there are some tutorails out there, but it is hard to google them~

@nicholas-leonard
Copy link
Member

@johnny5550822 Awesome! Keep us posted :)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants