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

value to set for weight_regularizer & dropout_regularizer when dataset size is unknown #12

Open
nikhil-salodkar opened this issue Dec 5, 2019 · 2 comments

Comments

@nikhil-salodkar
Copy link

Hi,

To calculate the value of weight_regularizer & dropout_regularizer the dataset_size N is used. What if we don't know the dataset size in advance like in case of Lifelong Reinforcement learning in which case re-training happens on a periodic basis on new data as it comes.

I am not able to figure out in such cases how we will be able to use this concrete dropout implementation.

Can you please suggest on how to handle such situations using Concrete dropout. Will really appreciate it.

Thanks in Advance
Nikhil

@JanRuettinger
Copy link

JanRuettinger commented Jul 12, 2020

I am facing the same issue. Did you find an answer?

@yaringal
Copy link
Owner

You can update N as the amount of data increases (have a look at this). In effect this will push the dropout p towards 0 in the limit of data

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