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

parameters of lsm #4

Open
shirleyatgithub opened this issue Nov 8, 2019 · 4 comments
Open

parameters of lsm #4

shirleyatgithub opened this issue Nov 8, 2019 · 4 comments

Comments

@shirleyatgithub
Copy link

Dear author,
Thanks for your generous sharing. Your code is very helpful for me to understand lsm.
I just wonder how you set the parameters to be the values they are now.

@anandtrex
Copy link
Contributor

Hi @shirleyatgithub , thank you for your message. The current parameters were chosen using a parameter search to achieve good performance on the XOR and memory tasks while maintaining reasonable firing rates and being close to asynchronous irregular firing.

@shirleyatgithub
Copy link
Author

Dear author,
Thanks for the reply. I wonder do you have any paper related to this project? I would like to read.

@shirleyatgithub
Copy link
Author

Dear author,
I have a question about the input_spikes. I see that the input_states are 666 pair of 0 and 1, and that corresponds to the targets (666 logits). But why the inp_spikes is 3226 elements with two array. How should I understand their meaning?
Thank you very much.

@anandtrex
Copy link
Contributor

anandtrex commented Dec 13, 2019

Hi @shirleyatgithub, this model was used in this paper.

Regarding your second question, can you point me to the specific line number where this happens?

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

2 participants