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

Update of behaviour of Sigma Neuron Dynamic Process in fixed-point representation #875

Merged

Conversation

ccaccavella
Copy link
Contributor

This update modifies the behavior of the Sigma Delta process in fixed-point representation, specifically within the PySigmaDeltaModelFixed process model. As this update introduces a breaking change, a new class named PySigmaDeltaModelFixedCorrected has been created instead of modifying the existing class.

Key Improvements
New Class Introduction: PySigmaDeltaModelFixedCorrected is introduced to encapsulate the corrected behavior.
Behavior: The new class alters only the delta dynamics, leaving the sigma and activation dynamics of the neuron model unchanged.
Truncation Error Compensation: The corrected delta dynamic keeps track of the last activation sent and compensates for truncation errors.

Usage Instructions
To utilize the PySigmaDeltaModelFixedCorrected class, you can either:

  1. Provide the exception_proc_model_map, or
  2. Write a custom RunConfig.

@bamsumit bamsumit requested a review from mathisrichter August 16, 2024 19:56
@mathisrichter mathisrichter merged commit 36bb33e into lava-nc:main Oct 29, 2024
5 checks passed
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

Successfully merging this pull request may close these issues.

3 participants