Repository navigation
Fix all known bugs for 0.3.5 (adopts #813 and #815) - #831
Merged
Merged
Conversation
…SRMNodes reset clears its spike window IzhikevichNodes sized its parameters by the n argument (None when only shape is given) and never reshaped them; CSRMNodes contracted with 'i,kij->kj'. Both now work for any shape; one-dimensional results are bit-identical (goldens conv2d_if_izh and csrm_window trial 0 unchanged). CSRMNodes.reset_state_variables now zeroes last_spikes, which changes results after a reset (csrm_window golden regenerated with that reason). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…with one channel
LocalConnection.compute dropped the batch dimension in its final view.
MaxPool{1,2,3}d multiplied a missing decay (None) and squeeze()d away a channel
of size 1; a missing decay now means plain spike counts, and the firing-rate
buffer follows the spike tensor's shape. Results that ran before are unchanged
(goldens pass). Reproducers kept as test_fixed_bug_stays_fixed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…; NetworkMonitor reset; tuple target shapes - MCC_LearningRule bounded sparse weights into a new tensor that only the rule held, so DiehlAndCook2015(sparse=True) never learned; the bound and the sparse normalisation now write in place. At batch 1 sparse and dense learn bit-identical weights without norm (test_sparse_dc2015_learns_like_dense); with norm they differ by summation order (max 6.0e-8). - MulticompartmentConnection.compute applies per-sample sparse weight copies ([batch, src, tgt]) with bmm; one copy keeps the old arithmetic. - NetworkMonitor.reset_state_variables looked connections up in layers. - [batch] + target.shape failed for tuple shapes. Results change: DiehlAndCook2015(sparse=True) now learns. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…work with batch > 1 - LearningRule.reset_state_variables deletes the tensors a rule creates on its first update (_step_state); AbstractConnection.reset_state_variables forwards to the rule. Reset then equals a freshly built network (invariant tests for mstdp_mstdpet and rules_mix now pass). Results change after a reset with learning on: goldens mstdp_mstdpet(_dt05), rules_mix(_dt05) regenerated, trial 0 bit-identical. - Rmax and MCC_learning.MSTDPET keep per-sample state and reduce the update over the batch, as MSTDP does. Batch 1 is bit-identical to the old formula (TestMccMstdpetBatched, goldens); batch 2 with sum equals the sum of single samples to summation order. Op counts at batch 1: MCC MSTDPET 24 -> 27, Rmax 24 -> 26 (regenerated with reason). API snapshot: +1 method. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
) Adopted from #813 (head 53dd2e3) by AHMETHAKANBEZIR1, reviewed with the bindsnet-pr-review skill (sandboxed canaries, fail-then-pass, API, timing); Hananel adopted it as accountable author because the PR says no human reviewed it. MeanFieldConnection.normalize scales w in place by norm over the absolute weight sum (a shared scalar counted once per target), instead of assigning a plain tensor to the Parameter (TypeError on every call). Co-Authored-By: Hananel Hazan <hananel@hazan.org.il> Co-Authored-By: OpenAI Codex <codex@openai.com>
Adopted from #815 (head 49c57f8) by AHMETHAKANBEZIR1, reviewed with the bindsnet-pr-review skill; Hananel adopted it as accountable author because the PR says no human reviewed it. Connection.compute_window re-creates s_w when the batch size changes, and reset_state_variables clears it for CSRM targets. Co-Authored-By: Hananel Hazan <hananel@hazan.org.il> Co-Authored-By: OpenAI Codex <codex@openai.com>
meanfield_norm and csrm_window goldens regenerated (both used to record a crash). Invariant xfails removed: reset-equals-fresh for csrm_window and meanfield_norm, round trip and batch for meanfield_norm. Still open: the CSRM spike window is not in the state_dict (round trip). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…ction drives CSRMNodes - Connection.s_w is a registered buffer, so state_dict saves it; a load adopts a saved window or drops one the saved state lacked (_load_window). The csrm_window round-trip invariant now passes; golden regenerated (adds s_w, no value changed). - MulticompartmentConnection.compute_window read s_w and self.w, neither of which it has, so MCC into CSRMNodes always raised. It now keeps a window of its own outputs (pipeline runs once per step), resized on a batch change, cleared on reset, saved in the state_dict. With static weights it matches a Connection bit for bit (test_multicompartment_into_csrm_matches_connection). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…_decay - compute() took the mean over the whole batch, so one sample's input depended on the others; it now uses each sample's own mean (batch 1 bit-identical: goldens pass without the weight_decay change). - weight_decay was passed by position into AbstractConnection's reduction slot and ignored; it is now passed by name. Results change for anyone who set weight_decay on a MeanFieldConnection (golden meanfield_decay regenerated with that reason). - Two #813 test lines expected the batch-wide mean (0.75); corrected to the per-sample means. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…on features at batch > 1, sparse weight bounds - topology_features.MeanField never called the base constructor (no name) and had no initial value; it now has an optional name, a placeholder value, and a per-sample mean ([batch, src, tgt], applied per sample by compute). - Sub-features (Normalization, Updating) get no-op prime_feature, update, normalize and reset_state_variables, which MulticompartmentConnection calls on every pipeline entry; both now work in the constructor and in Network.run. - AdaptationBaseSynapsHistory/OtherSynaps: a synapse is active when its pre-synaptic neuron spiked in any sample (the mask is shared connectivity); batch 1 gives the same values. - Sparse weights with wmin/wmax: Connection.__init__ bounds a dense copy, LearningRule.update bounds in place via a dense copy, and WeightDependentPostPre/DiehlAndCook compute their factors from a dense view. PostPre, WeightDependentPostPre and DiehlAndCook on a bounded SparseConnection learn bit-identical weights to the dense Connection. - Test workarounds for these bugs removed (batch-1-only sets, broken pairs, tuple-shape and sparse-bound special cases). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
…mpartmentConnection feature values in the state_dict - MulticompartmentConnection saves its pipeline feature values as feature.<name> and loads them in place, so DiehlAndCook2015 can be saved and restored (the last four strict xfails in test_invariants.py now pass; dc2015 goldens regenerated: new keys, no value changed). - Every KNOWN_BUGS entry is fixed: the dict becomes FIXED_BUGS (reproducers that must keep running); the empty xfail machinery in test_invariants.py and the batch-1, no-learning-check and sub-feature workarounds in test_all_classes.py are removed, so those classes run at batch 2 with full checks. - CONTRIBUTING, PR template and bindsnet/learning/README.md updated. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Network (reviewer B): - MulticompartmentConnection state_dict: refuses to save duplicate feature names (they shared one key, and loading put one feature's value into the other); checks shape and sparse layout on load (copy_ broadcast a wrong-shaped tensor silently); saves the adaptation features' mask, spike buffer and counter (only value was saved). - An Updating sub-feature drives its parent's learning; the connection's update skips that parent (it learned twice per step). - A sub-feature whose parent is not in the pipeline is refused at construction (it failed later with an unclear TypeError). insert_pipeline had list.insert's arguments swapped. - Connection.compute_window and MaxPool resets create state on the spikes' device (CUDA device mismatch, also on master). - Docstrings state how the two CSRM windows differ once weights learn. Learning rules (reviewer A): - MCC_learning.DiehlAndCook crashed on sparse weights (twin of the learning.py fix). Sparse MCC weight copies now all get the batch's shared update in PostPre, DiehlAndCook and MSTDPET (as MSTDP did), so sparse equals dense; the default squeeze reduction means a sum over a larger batch, as in the fused dense path (_reduce_batch, _add_to_feature). - Docs: per-sample reward shape [batch, 1, 1]; reset keeps the reduction chosen at construction. CHANGELOG: checkpoint compatibility (strict=False for old checkpoints), new state shapes, sparse and Updating semantics. Each fix has a test that fails on ce98f93 and passes here. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
3 tasks done
Hananel-Hazan
added
the
tests-changed-ok
Hananel-Hazan
added a commit
that referenced
this pull request
Oct 29, 2026
* fix: IzhikevichNodes and CSRMNodes accept multi-dimensional shapes; CSRMNodes reset clears its spike window
IzhikevichNodes sized its parameters by the n argument (None when only shape is
given) and never reshaped them; CSRMNodes contracted with 'i,kij->kj'. Both now
work for any shape; one-dimensional results are bit-identical (goldens
conv2d_if_izh and csrm_window trial 0 unchanged). CSRMNodes.reset_state_variables
now zeroes last_spikes, which changes results after a reset (csrm_window
golden regenerated with that reason).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: LocalConnection batch > 1; MaxPool connections without decay or with one channel
LocalConnection.compute dropped the batch dimension in its final view.
MaxPool{1,2,3}d multiplied a missing decay (None) and squeeze()d away a channel
of size 1; a missing decay now means plain spike counts, and the firing-rate
buffer follows the spike tensor's shape. Results that ran before are unchanged
(goldens pass). Reproducers kept as test_fixed_bug_stays_fixed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: sparse MulticompartmentConnection learns and runs with batch > 1; NetworkMonitor reset; tuple target shapes
- MCC_LearningRule bounded sparse weights into a new tensor that only the rule
held, so DiehlAndCook2015(sparse=True) never learned; the bound and the
sparse normalisation now write in place. At batch 1 sparse and dense learn
bit-identical weights without norm (test_sparse_dc2015_learns_like_dense);
with norm they differ by summation order (max 6.0e-8).
- MulticompartmentConnection.compute applies per-sample sparse weight copies
([batch, src, tgt]) with bmm; one copy keeps the old arithmetic.
- NetworkMonitor.reset_state_variables looked connections up in layers.
- [batch] + target.shape failed for tuple shapes.
Results change: DiehlAndCook2015(sparse=True) now learns.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: MSTDP/MSTDPET/Rmax state cleared on reset; Rmax and MCC MSTDPET work with batch > 1
- LearningRule.reset_state_variables deletes the tensors a rule creates on its
first update (_step_state); AbstractConnection.reset_state_variables forwards
to the rule. Reset then equals a freshly built network (invariant tests for
mstdp_mstdpet and rules_mix now pass). Results change after a reset with
learning on: goldens mstdp_mstdpet(_dt05), rules_mix(_dt05) regenerated,
trial 0 bit-identical.
- Rmax and MCC_learning.MSTDPET keep per-sample state and reduce the update
over the batch, as MSTDP does. Batch 1 is bit-identical to the old formula
(TestMccMstdpetBatched, goldens); batch 2 with sum equals the sum of single
samples to summation order. Op counts at batch 1: MCC MSTDPET 24 -> 27,
Rmax 24 -> 26 (regenerated with reason). API snapshot: +1 method.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: preserve the mean-field weight parameter during normalization (#813)
Adopted from #813 (head 53dd2e3) by AHMETHAKANBEZIR1, reviewed with the
bindsnet-pr-review skill (sandboxed canaries, fail-then-pass, API, timing);
Hananel adopted it as accountable author because the PR says no human
reviewed it. MeanFieldConnection.normalize scales w in place by norm over the
absolute weight sum (a shared scalar counted once per target), instead of
assigning a plain tensor to the Parameter (TypeError on every call).
Co-Authored-By: Hananel Hazan <hananel@hazan.org.il>
Co-Authored-By: OpenAI Codex <codex@openai.com>
* fix: reset and resize the CSRM connection spike history (#815)
Adopted from #815 (head 49c57f8) by AHMETHAKANBEZIR1, reviewed with the
bindsnet-pr-review skill; Hananel adopted it as accountable author because the
PR says no human reviewed it. Connection.compute_window re-creates s_w when the
batch size changes, and reset_state_variables clears it for CSRM targets.
Co-Authored-By: Hananel Hazan <hananel@hazan.org.il>
Co-Authored-By: OpenAI Codex <codex@openai.com>
* test: goldens and invariants after adopting #813 and #815
meanfield_norm and csrm_window goldens regenerated (both used to record a
crash). Invariant xfails removed: reset-equals-fresh for csrm_window and
meanfield_norm, round trip and batch for meanfield_norm. Still open: the CSRM
spike window is not in the state_dict (round trip).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: CSRM spike window saved in the state_dict; MulticompartmentConnection drives CSRMNodes
- Connection.s_w is a registered buffer, so state_dict saves it; a load adopts
a saved window or drops one the saved state lacked (_load_window). The
csrm_window round-trip invariant now passes; golden regenerated (adds s_w,
no value changed).
- MulticompartmentConnection.compute_window read s_w and self.w, neither of
which it has, so MCC into CSRMNodes always raised. It now keeps a window of
its own outputs (pipeline runs once per step), resized on a batch change,
cleared on reset, saved in the state_dict. With static weights it matches a
Connection bit for bit (test_multicompartment_into_csrm_matches_connection).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: MeanFieldConnection keeps batch samples apart and applies weight_decay
- compute() took the mean over the whole batch, so one sample's input depended
on the others; it now uses each sample's own mean (batch 1 bit-identical:
goldens pass without the weight_decay change).
- weight_decay was passed by position into AbstractConnection's reduction
slot and ignored; it is now passed by name. Results change for anyone who
set weight_decay on a MeanFieldConnection (golden meanfield_decay
regenerated with that reason).
- Two #813 test lines expected the batch-wide mean (0.75); corrected to the
per-sample means.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: MeanField feature, Normalization/Updating sub-features, adaptation features at batch > 1, sparse weight bounds
- topology_features.MeanField never called the base constructor (no name) and
had no initial value; it now has an optional name, a placeholder value, and
a per-sample mean ([batch, src, tgt], applied per sample by compute).
- Sub-features (Normalization, Updating) get no-op prime_feature, update,
normalize and reset_state_variables, which MulticompartmentConnection calls
on every pipeline entry; both now work in the constructor and in Network.run.
- AdaptationBaseSynapsHistory/OtherSynaps: a synapse is active when its
pre-synaptic neuron spiked in any sample (the mask is shared connectivity);
batch 1 gives the same values.
- Sparse weights with wmin/wmax: Connection.__init__ bounds a dense copy,
LearningRule.update bounds in place via a dense copy, and
WeightDependentPostPre/DiehlAndCook compute their factors from a dense view.
PostPre, WeightDependentPostPre and DiehlAndCook on a bounded
SparseConnection learn bit-identical weights to the dense Connection.
- Test workarounds for these bugs removed (batch-1-only sets, broken pairs,
tuple-shape and sparse-bound special cases).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test: known-bug list becomes FIXED_BUGS; workarounds removed; MulticompartmentConnection feature values in the state_dict
- MulticompartmentConnection saves its pipeline feature values as
feature.<name> and loads them in place, so DiehlAndCook2015 can be saved
and restored (the last four strict xfails in test_invariants.py now pass;
dc2015 goldens regenerated: new keys, no value changed).
- Every KNOWN_BUGS entry is fixed: the dict becomes FIXED_BUGS (reproducers
that must keep running); the empty xfail machinery in test_invariants.py and
the batch-1, no-learning-check and sub-feature workarounds in
test_all_classes.py are removed, so those classes run at batch 2 with full
checks.
- CONTRIBUTING, PR template and bindsnet/learning/README.md updated.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* docs: CHANGELOG for the 0.3.5 bug fixes, results changes listed first
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* fix: issues found by independent review of PR #831
Network (reviewer B):
- MulticompartmentConnection state_dict: refuses to save duplicate feature
names (they shared one key, and loading put one feature's value into the
other); checks shape and sparse layout on load (copy_ broadcast a wrong-shaped
tensor silently); saves the adaptation features' mask, spike buffer and
counter (only value was saved).
- An Updating sub-feature drives its parent's learning; the connection's
update skips that parent (it learned twice per step).
- A sub-feature whose parent is not in the pipeline is refused at construction
(it failed later with an unclear TypeError). insert_pipeline had list.insert's
arguments swapped.
- Connection.compute_window and MaxPool resets create state on the spikes'
device (CUDA device mismatch, also on master).
- Docstrings state how the two CSRM windows differ once weights learn.
Learning rules (reviewer A):
- MCC_learning.DiehlAndCook crashed on sparse weights (twin of the learning.py
fix). Sparse MCC weight copies now all get the batch's shared update in
PostPre, DiehlAndCook and MSTDPET (as MSTDP did), so sparse equals dense; the
default squeeze reduction means a sum over a larger batch, as in the fused
dense path (_reduce_batch, _add_to_feature).
- Docs: per-sample reward shape [batch, 1, 1]; reset keeps the reduction chosen
at construction.
CHANGELOG: checkpoint compatibility (strict=False for old checkpoints), new
state shapes, sparse and Updating semantics. Each fix has a test that fails on
ce98f93 and passes here.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* ci: close test-guard bypasses found by independent review (WIP part 1)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* test: op-count workloads for every Nodes class
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
* ci: close the test-guard bypasses found by independent review (part 2), docs
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
Co-authored-by: AHMETHAKANBEZIR1 <ahmethakan0008@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
This was referenced Oct 29, 2026
Merged
This file contains hidden or 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
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.
What this changes and why
This fixes every bug the test-hardening work (#828) pinned on master: the 25 entries of
KNOWN_BUGSand the 15 strict expected failures intest/regression/test_invariants.py(40 in total). It also fixes the bugs found while doing that. On Hananel's decision, all of these fixes ship in 0.3.5, including the ones that change results.CHANGELOG.mdlists those first, under Results changes.Two contributor PRs are adopted, with the contributor kept as git author: #813 (
MeanFieldConnection.normalize) and #815 (CSRM connection spike window). Both were reviewed with thebindsnet-pr-reviewskill. Both said no human had reviewed the code, so Hananel adopted them as accountable author. Two lines of #813's tests expected the batch-wide mean (0.75), which is the batch-mixing bug fixed here. They were corrected to the per-sample means.Results changes (also in CHANGELOG)
reset_state_variables()clears theMSTDP,MSTDPETandRmaxtraces. Affectsbreakout_stdp.pyanddot_tracing.py.CSRMNodesand its connection clear their spike windows on reset.DiehlAndCook2015now learns.DiehlAndCook2015(sparse=True)never changed its weights before. With one sample it now learns bit-identical weights to the dense model.MeanFieldConnectionappliesweight_decay. It was ignored before.MeanFieldConnectionand theMeanFieldfeature use each sample's own mean. Batch size 1 is unchanged.Saved outputs regenerated, each with its reason:
csrm_window,mstdp_mstdpet,mstdp_mstdpet_dt05,rules_mix,rules_mix_dt05,meanfield_norm,meanfield_decay. In every case trial 0 is bit-identical where the change only acts after a reset.dc2015_b1anddc2015_b16only gained new state keys (the weights are now instate_dict); no value changed.Evidence
test/network/test_perf_equivalence.py, CLAUDE.md rule):MCC_learning.MSTDPETat batch size 1 is bit-identical to the old one-dimensional formula, at dt 1 and 0.5.sumequals the sum of single samples, to summation order (rtol 1e-6). The same holds forRmax.MCC_learning.MSTDPET24 → 27,Rmax24 → 26. The increase comes from per-sample state (batched matrix products and a reduction over the batch); regenerated with that reason.MeanFieldgains an optionalname.review.py --local-ref). It stopped at its gate because this branch changes binary golden files and.github/; it needs Hananel's clearance for the exact commit.Checklist
poetry run pytestpassed locally.bug-testcheck).--reason.op_counts.json,api_surface.json,FIXED_BUGS(wasKNOWN_BUGS). Theweakened-testscheck lists them: the removedtest_known_bug_still_failsand the removed expected-failure markers are fixes, not weakening. Needs thetests-changed-oklabel.Unreleasedupdated.🤖 Generated with Claude Code