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.

Sign up for GitHub

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

Jump to bottom

Tutorial 5: Why do we need to iterate over the same sample in forward function of the network is the input data does not have a time dimension #373

Open
SM1991CODES opened this issue Mar 6, 2025 · 0 comments
Open

Tutorial 5: Why do we need to iterate over the same sample in forward function of the network is the input data does not have a time dimension #373

SM1991CODES opened this issue Mar 6, 2025 · 0 comments

Comments

@SM1991CODES
Copy link

Image

  1. The input is just a normal batch of MNIST images - Bx784 or Bx1x784, why do we feed in the batch repeatedly? The LIF layers would generate spikes even with a single pass and then it eventually learns to generate correct number of spikes without having to repeat the input - is this assumption correct? Why are we not using time axis at the input and not converting MNIST to spikes at input?
    How does this relate to actual event/ spike based sensors when used for applications?

  2. v_mem get's reset at each batch, but should it not be maintained across batches?
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@SM1991CODES