Dev/improve learning sim #500
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…into dev/learning_rc_0.5
…into dev/learning_rc_0.5
…to dev/learning_three_factor
10 tasks
bala-git9
approved these changes
Nov 28, 2022
weidel-p
approved these changes
Dec 5, 2022
monkin77
pushed a commit
to monkin77/thesis-lava
that referenced
this pull request
Jul 12, 2024
* inheritance from base class * inheritance from base connection * floating point model * minor cleanup * added neuron base class * separate models from process files * rm init file * inherit from Neuron and Connection * merged LearningDense into Dense * release candidate 0.5 * beginning last clean * clean in progress * updated tutorial * changes according to checklist made. missing use of np.where refactor * changed evaluate_trace to use boolean indexing instead of np.where * removed BITS_ * lint and poetry update * moved tutorial to in_depth * Licenses * lint tests * poetry update * docstrings for connection and learning rule * fixing typo * minor optimization for floating point model * added learning related unit tests * added other learning related unit tests * refactored docstrings * merged Loihi1 and 2 LearningRules and added seed for RNGs * added neuon base class and three fac learning rule * minor changes * Adding R-STDP wrapper and tutorial skeleton * Adding decay to tag * adding LearningLIF process and update tutorial * adding LearningLIF process model * Modifying reward trace based on graded input * Update LearningLIF to include graded input spikes * Updated tutorial * Updating unit tests * Fixing errors * Editing tutorial text * modified tutorial and fixing dangling ports * adding tutorial_helper func * adding some plots to tutorial * Merge origin/main to origin/dev/learning_three_factor * added graded in ports to LearningDense and fixing tutorial plots * changes structure * added minor changes to stdo tutorials * fixing np.logical_and/or problems * tutorial polishing * weights plot fixed * fixing graded input ports in Dense * fixing lint errors * fixing LearningLIF run_spk * tutorial text changes * fixing lint errors * lint issues * annoying white spaces fixed * removing enable_learning flag * adding plot explanations * fixing rstdp wrapper * fix the stdp tests. minor update to structure * minor change * Saving tutorial text updates to new file. Avoiding merge conflict. * add y1 ports and major changes to the learning rules * minor changes * changing plastic to learning and wrapper name * fixed bugs and inconsistencies, moved RSTDP LIF to tutorial * including float to literal str * fixing lint errors * modifying tutorial * fixing lif tests * removing LearningLIF test * fixing tutorial image * changing tutorial name * moving image to lava-docs * fixing some of the comments from AW * renames run_spk in connection, HCand UC to 2F resp 3F, docstrings ands tests * fetch pyproject and lock from main * fixing tutorials plots, changing docstrings * adding tutorial text * changing y3 to function as y0 * changing functionality of y3 * changing y1 as y0, fixing tutorial plots for workshop * changing reward traces in tutorial * adding neuron picture * changing reward traces * minor change * avoid explosion of dimensionality in evaluate traces in floating point * minor change * adding bit acc/approx versions * first steps in optimizing new evaluate trace algorithm * fixing the post-traces update * adding unittests * Adapting LearningDense PMs to use new implementation * fixing A+/- * adding figures to lava-docs * minor change * correcting flipped A_plus/A_minus * fixing lint errors * removing comments in stdp_test * adding documentation to improved implementation of evaluate_traces * fixing learning_rule_applier tests * flipping A_plus and A_minus in tests, tests passing * minor change to RSTDP tutorial * changing recv_traces for 3FLearningRule * removing update_dependencies from run_lrn * adapting rstdp to new version * fixed tests * correcting 3F tutorial Co-authored-by: Philipp <[email protected]> Co-authored-by: gkarray <[email protected]> Co-authored-by: bala <[email protected]> Co-authored-by: drager-intel <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Issue Number:
Objective of pull request: Changes to the Learning API, learning-related tests and tutorials to address the following points :
Pull request checklist
Your PR fulfills the following requirements:
flakeheaven lint src/lava tests/) and (bandit -r src/lava/.) pass locallypytest) passes locallyPull request type
Please check your PR type:
What is the current behavior?
What is the new behavior?
Does this introduce a breaking change?
Supplemental information