Papers › Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits...

Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis

16 Jun 2023NeurIPS 2023 11arXiv:2306.10168archive 2025-07-28

Mitchell Ostrow, Adam Eisen, Leo Kozachkov, Ila Fiete

How can we tell whether two neural networks utilize the same internal processes for a particular computation? This question is pertinent for multiple subfields of neuroscience and machine learning, including neuroAI, mechanistic interpretability, and brain-machine interfaces. Standard approaches for comparing neural networks focus on the spatial geometry of latent states. Yet in recurrent networks, computations are implemented at the level of dynamics, and two networks performing the same computation with equivalent dynamics need not exhibit the same geometry. To bridge this gap, we introduce a novel similarity metric that compares two systems at the level of their dynamics, called Dynamical Similarity Analysis (DSA). Our method incorporates two components: Using recent advances in data-driven dynamical systems theory, we learn a high-dimensional linear system that accurately captures core features of the original nonlinear dynamics. Next, we compare different systems passed through this embedding using a novel extension of Procrustes Analysis that accounts for how vector fields change under orthogonal transformation. In four case studies, we demonstrate that our method disentangles conjugate and non-conjugate recurrent neural networks (RNNs), while geometric methods fall short. We additionally show that our method can distinguish learning rules in an unsupervised manner. Our method opens the door to comparative analyses of the essential temporal structure of computation in neural circuits.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 17 code samples harvested from 1 repository linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 17 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mitchellostrow/dsa officialmentioned in papermentioned on GitHubpytorchMITSyntology: 17 samples, 9 ran (0 instrument-failed) · 8 unverified report
qglht/repal mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula... (arXiv:2406.01589; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

17 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

9ran
8unverified

Licence: 0 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mitchellostrow/dsa. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

mitchellostrow/dsa official repository 17 samples, 9 ran (0 instrument-failed) · 8 unverified
coarse_grain DSA/preprocessing.py ran MIT (permissive) · ce82b9159690e201 · report fixture: signature trajectories:ndarray/3/float, bin_size:int/0/int, bins_overlapping:int/0/int · returned ndarray · level recorded 2026-09-26
compute_angle in 8 papers DSA/simdist.py ran MIT (permissive) · f619414f24f51acd · report fixture: signature evec:ndarray/2/complex · returned Tensor · level recorded 2026-09-26
embed_signal_torch DSA/dmd.py ran fingerprinted MIT (permissive) · 727929ee435d8106 · report fixture: signature data:Tensor/2/float, n_delays:int/0/int, delay_interval:int/0/int · returned Tensor · level recorded 2026-09-26
mae in 41 papers
census: 4 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
DSA/stats.py ran MIT (permissive) · 43a5b3592b84536d · report fixture: signature x:ndarray/2/float, y:Tensor/2/float · returned float · level recorded 2026-09-26
mase DSA/stats.py ran fingerprinted MIT (permissive) · aa9cf3edabb13e0d · report fixture: signature true_vals:Tensor/2/float, pred_vals:Tensor/2/float · returned float · level recorded 2026-09-26
normalize_data in 32 papers
census: 7 implementations from 7 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
DSA/preprocessing.py ran MIT (permissive) · f56b12d183adacab · report fixture: signature data_list:list/1/ndarray · returned list · level recorded 2026-09-26
normalize_dataset in 5 papers DSA/preprocessing.py ran fingerprinted MIT (permissive) · be99d312201d0c3d · report fixture: signature data:ndarray/3/float · returned ndarray · level recorded 2026-09-26
split_train_test in 9 papers DSA/sweeps.py ran MIT (permissive) · 16779f71fd8051f6 · report fixture: signature data:list/1/Tensor, train_frac:float/0/float · returned tuple · level recorded 2026-09-26
torch_convert DSA/stats.py ran MIT (permissive) · e1d6e88bffac80b7 · report fixture: signature x:ndarray/2/float · returned Tensor · level recorded 2026-09-26
compute_residuals DSA/resdmd.py unverified MIT (permissive) · 2c07e6403bc87552 · report
compute_residuals_pykoopman DSA/resdmd.py unverified MIT (permissive) · 70f1203a7cd08d77 · report
compute_residuals_subspace_dmdc DSA/resdmd.py unverified MIT (permissive) · 4b89656fc2246ff0 · report
compute_subspace_angles DSA/simdist.py unverified MIT (permissive) · e56244a3bcbf33c4 · report
embed_data_DMDc DSA/dmdc.py unverified MIT (permissive) · 43f545258d864847 · report
pad_zeros DSA/simdist.py unverified MIT (permissive) · fb3e7fc8f5aae568 · report
sweep_local_dmd DSA/sweeps.py unverified MIT (permissive) · dea4ecf3be0f5736 · report
sweep_pykoopman DSA/sweeps.py unverified MIT (permissive) · aa3a546937bafe14 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

FocusProcrustes

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections