-
Notifications
You must be signed in to change notification settings - Fork 357
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
Enhance e-prop plasticity with biologically inspired features #3207
base: master
Are you sure you want to change the base?
Conversation
Co-authored-by: JesusEV <espinozavalverd@uni-wuppertal.de>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
…e multiplication Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com>
* move to eprop_archiving_node * introduce more surrogate gradients * introduce width scaling factor beta
Co-authored-by: JesusEV <jesus.espinoza.val@gmail.com> Co-authored-by: Hans Ekkehard Plesser <hans.ekkehard.plesser@nmbu.no>
Fix consistency
This reverts commit 32fa32a.
Test for batch size 2
* fix pylint error "possibly-used-before-assignment"
Test classification for batch_size 2
@JesusEV Thanks for the updates, I just started to review and I have a question about the model names: Here is the list I see (autogenerated list of models):
And |
@JesusEV @heplesser @clinssen @akorgor This is what I understand: The problem I have is that I think we can keep the file names as they are as is the convention. What do you all think? |
Hi, thanks for the contributions! Would it be possible to run us reviewers through this PR at the next NEST hackathon, June 19-21? |
@jessica-mitchell Yes, you're correct—there are two distinct sets of models. Regarding the naming scheme, we decided on this nomenclature during a previous meeting with all authors involved. However, your concern highlights that it might be confusing. Thanks for bringing this to our attention! This topic should be revisited during the next meeting, scheduled probably for the week of June 19-21. |
This PR extends the previous efforts (PR #2867 "Implement e-prop plasticity") in porting the eligibility propagation (e-prop) plasticity mechanism by Bellec et al. (2020) from TensorFlow to NEST by introducing several novel, bio-inspired enhancements to e-prop.
Changes
_bsshslm_2020
, aligning with NEST's naming convention that reflects the first letters of the authors' last names and the publication year.eprop_iaf
eprop_iaf_psc_delta
eprop_iaf_adapt
eprop_readout
eprop_synapse
eprop_learning_signal_connection
eprop_archiving_node
with added support for new models.test_eprop_plasticity.py
eprop_supervised_regression_sine-waves.py
eprop_supervised_classification_neuromorphic_mnist.py
eprop_supervised_classification_evidence-accumulation.py
A manuscript by Korcsak-Gorzo, Stapmanns, and Espinoza Valverde et al. detailing these enhancements is in preparation.
References
Bellec G, Scherr F, Subramoney F, Hajek E, Salaj D, Legenstein R, Maass W (2020). A solution to the learning dilemma for recurrent networks of spiking neurons. Nature Communications, 11:3625. DOI
Korcsak-Gorzo A, Stapmanns J, Espinoza Valverde JA, Dahmen D, van Albada SJ, Plesser HE, Bolten M, Diesmann M. Event-based implementation of eligibility propagation. (in preparation)
Co-authored-by: Agnes Korcsak-Gorzo 40828647+akorgor@users.noreply.github.com