Pretraining of Embodied Recurrent Networks Bridges the Gap Between Artificial and Cortical Neural Activities.
8 blocks of code here have a permanent identifier (oscr:b:…), listed with the matches below: citable for good, with a page of its own. Select a match and press Cite to copy it. What a block identifier is.
The 8 matches · 3 of them tie a paragraph to a whole file without given lines: weak matches, whose lines are not tinted
- [1] § 3. Results › 3.2. The SR Model Shows Enhanced Alignment with Biological Neural Geometry and Dynamics ↔ analysis/run_model_comparison.py, the whole file · a weak match · score 0.77 · Kruskal Wallis, SR Dense, model comparison, DR Multi, CO Single, Friedman · block
oscr:b:ATSC4DM6B3VF6-4· Report a mismatch - [2] § 3. Results › 3.2. The SR Model Shows Enhanced Alignment with Biological Neural Geometry and Dynamics ↔ analysis/run_stats_dsa.py, the whole file · a weak match · score 0.63 · SR Dense, DR Multi, CO Single, pairwise, Moderate, ranking · block
oscr:b:S6WB6K02T2JYM-H· Report a mismatch - [3] § 3. Results › 3.2. The SR Model Shows Enhanced Alignment with Biological Neural Geometry and Dynamics ↔ figures/fig7.py, lines 148 to 187 · score 0.60 · CO Multi model, SR model, CO Single, dense, CC, AUC · block
oscr:b:TMTAPTT0BF0ND-7· Report a mismatch - [4] § 2. Materials and Methods › 2.1. Model Architecture › 2.1.2. Musculoskeletal Arm Model ↔ training/train_dr.py, lines 177 to 252 · score 0.60 · RigidTendonHillMuscle, RigidTendonArm26, nn, proprioceptive, class, effector · block
oscr:b:MJ0GACDHAHFZK-L· Report a mismatch - [5] § 2. Materials and Methods › 2.2. Task Representations and Training Procedure › 2.2.4. Training Procedure ↔ tasks/grid_reach.py, lines 75 to 161 · score 0.59 · 100–300 ms, catch trial, uniformly, GO, 100 ms, joint · block
oscr:b:04QJ3F03JB5XC-P· Report a mismatch - [6] § 3. Results › 3.1. Behavioral Performance and Neural Activity of the Single-Reach Model ↔ analysis/eval_BasicModel.py, lines 20 to 54 · score 0.59 · 0.05–0.35, reaching distance, joint space, Cartesian, workspace, intervals · block
oscr:b:3145KEMT3HB07-X· Report a mismatch - [7] § 2. Materials and Methods › 2.1. Model Architecture › 2.1.2. Musculoskeletal Arm Model ↔ scripts/pre_data.py, the whole file · a weak match · score 0.58 · RigidTendonHillMuscle, RigidTendonArm26, pre, angles, class, effector · block
oscr:b:8V33XAT37708D-6· Report a mismatch - [8] § 3. Results › 3.1. Behavioral Performance and Neural Activity of the Single-Reach Model ↔ model/build.py, lines 83 to 132 · score 0.57 · angle intervals, reaching distance, joint space, Cartesian, workspace, model · block
oscr:b:PW3HFE0379YCY-E· Report a mismatch
Paper
Loaded from Europe PMC by your browser; OSCR does not store it: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
Python · 40 lines · 1.5 KB · no license · 1 match
- import numpy as np
- from itertools import combinations
- from scipy.stats import friedmanchisquare, wilcoxon, kruskal
- models = ["SR_Dense", "SR_Moderate", "SR_Sparse",
- "CO_Single", "CO_Multi", "DR_Single", "DR_Multi"]
- model_idx = {label: i for i, label in enumerate(
- ["MC_agg", "MM_agg", "SR_Dense", "SR_Moderate", "SR_Sparse",
- "CO_Single", "CO_Multi", "DR_Single", "DR_Multi"])}
- file_name = "Data/CO/"
- for fname, monkey in [("DSA_C.npy", "Monkey C"), ("DSA_M.npy", "Monkey M")]:
- arr = np.load(file_name+fname)
- print(f"\n{monkey}")
- data = np.array([arr[model_idx[m]] for m in models])
- stat, p = friedmanchisquare(*data)
- print(f"Friedman: chi2={stat:.3f}, p={p:.6f}")
- pairs = []
- for a, b in combinations(range(7), 2):
- w, p_w = wilcoxon(data[a], data[b])
- pairs.append({"m1": models[a], "m2": models[b],
- "diff": float(np.mean(data[a] - data[b])), "p": p_w})
- pairs.sort(key=lambda x: x["p"])
- for r, pr in enumerate(pairs):
- pr["adj"] = 0.05 / (len(pairs) - r)
- pr["reject"] = pr["p"] < pr["adj"]
- sig = [p for p in pairs if p["reject"]]
- print(f" Sig: {len(sig)}/{len(pairs)}")
- for pr in sig:
- print(f" {pr['m1']:15s} vs {pr['m2']:15s} diff={pr['diff']:+8.6f} p={pr['p']:.6f}")
- sr = data[[0, 1, 2]].ravel()
- co = data[[3, 4]].ravel()
- dr = data[[5, 6]].ravel()
- h, p_k = kruskal(sr, co, dr)
- print(f" Kruskal-Wallis (SR vs CO vs DR): H={h:.3f}, p={p_k:.6f}")
run_model_comparison.py at commit 7a85393, no license · at the source
Overview
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China; (X.B.); (H.J.)
- Graduate School of Biomedical Engineering, University of New South Wales, Sydney, NSW 2052, Australia
- Department of Physical Education, Shanghai Jiao Tong University, Shanghai 200240, China
Abstract
Task-driven recurrent neural networks (RNNs) have been widely employed as tools for investigating neural dynamics in neural motor control research by modeling the motor cortex. RNNs are often implicitly assumed to learn the underlying computational mechanisms in accordance with biological neural circuits. However, the brain network has a highly structured and specific network connectivity and during individual development the motor cortex has acquired a rich repertoire of behavioral primitives via continuous learning of body control. Considering that the task-driven RNNs are often initialized randomly and trained directly on the specific task, how much these models can truly reveal about the motor cortex is still a crucial question awaiting further research. In this study, we propose a method for modeling the motor cortex pretrained on single reaching skills. Specifically, we use an RNN, receiving sensory feedback and task inputs, as the controller to produce motor commands that drive a musculoskeletal arm model. This model can perform reaching movements along a mini-jerk trajectory between arbitrary points in the workspace, prior to training on specific tasks. The model pretrained on single-reach task has more similarity with real neural data both on a neural geometry and neural dynamics level in center-out (CO) and random target touch (RTT) tasks than models directly trained on these tasks. Surprisingly, we observed the opposite pattern in a double-reach (DR) task, in which two targets appeared simultaneously, rather than presenting the next target after the completion of the prior movement as in the RTT task. This suggests that sequential movements are planned as an integrated unit, and this capability may be implemented at the level of motor cortical circuits. In summary, our results suggest that endowing the network with capabilities beyond the immediate task demands—through more systematic training or other methods—can help better understand the dynamics of biological neural circuits.
Reproduced under the paper's license (CC BY), from the paper cited above.
Repository
Its files are read in the Code ↔ Paper reader above, with 8 matches between paragraphs and lines of code.
RevuBu/Pretrained_RNN
7a853932e22cc30a1f38185ec562f5f2058d0a49, 31 July 2026Availability: 1 check, the latest on 27 September 2026: the link answers
- 27 September 2026: the link answers
35 files
- analysis/
Compute_CO_DSA.py , Python, 38 lines - analysis/
Compute_rtt_DSA.py , Python, 82 lines - analysis/
Melting.py , Python, 129 lines - analysis/
__init__.py , Python, 2 lines - analysis/
eval_BasicModel.py , Python, 182 lines, 1 match - analysis/
run_model_comparison.py , Python, 40 lines, 1 match - analysis/
run_stats_auc.py , Python, 184 lines - analysis/
run_stats_dsa.py , Python, 71 lines, 1 match - analysis/
run_stats_rtt.py , Python, 55 lines - figures/
__init__.py , Python, 1 line - figures/
fig3.py , Python, 435 lines - figures/
fig4.py , Python, 249 lines - figures/
fig5.py , Python, 231 lines - figures/
fig6.py , Python, 155 lines - figures/
fig7.py , Python, 199 lines, 1 match - model/
__init__.py , Python, 2 lines - model/
build.py , Python, 132 lines, 1 match - model/
rnn.py , Python, 201 lines - scripts/
__init__.py , Python, 1 line - scripts/
pre_CO_data.py , Python, 89 lines - scripts/
pre_DR_data.py , Python, 145 lines - scripts/
pre_data.py , Python, 62 lines, 1 match - setup.py, Python, 22 lines
- tasks/
__init__.py , Python, 3 lines - tasks/
grid_reach.py , Python, 459 lines, 1 match - tasks/
kinematics.py , Python, 72 lines - tasks/
sequential_reach.py , Python, 653 lines - training/
__init__.py , Python, 2 lines - training/
params.py , Python, 58 lines - training/
pretrain_grid.py , Python, 157 lines - training/
train_co.py , Python, 160 lines - training/
train_dr.py , Python, 252 lines, 1 match - training/
train_rtt.py , Python, 186 lines - training/
utils.py , Python, 175 lines - README.md, Text, 74 lines
The paper's code and data availability statement is in the Data section.
Tracing map
Proposed by the machine: these links were found in the paper and verified at the source, without human review. The map will receive a Zenodo DOI once one of the paper's authors has validated it with their ORCID.
What the map holds:
- 1 repository of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 34 scripts, each with its path and the digest of its content;
- 8 matches between paragraphs of the paper and lines of the code (method lexical-v1);
- neither the text of the paper nor the code itself.
Its JSON (tracing-map.json) is deposited on Zenodo with its DOI once the map is validated.
Data
Datasets cited
- crcns.org/
data-sets/ , at CRCNS; found in the referencesmotor-cortex
Data Availability Statement
The original contributions presented in this study are included in the article. The custom code used for this study will be made publicly available on GitHub (https://
Reproduced under the paper's license (CC BY), from the paper cited above.
Versions
The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.
Version 1, 27 September 2026: the first record
Recorded: type, language, journal, volume, issue, pages, dates, 5 authors, 5 keywords, 3 funders, 92 references.
Cite
This paper
Bu, X., Jiang, H., Guo, T., Li, H., & Chen, Y. (2026). Pretraining of Embodied Recurrent Networks Bridges the Gap Between Artificial and Cortical Neural Activities. Biomimetics (Basel, Switzerland), 11(8), 569. https://
BibTeX
@article{bu2026pretraini
author = {Bu, Xiangdong and Jiang, Hongru and Guo, Tianruo and Li, Heng and Chen, Yao},
title = {{Pretraining of Embodied Recurrent Networks Bridges the Gap Between Artificial and Cortical Neural Activities}},
journal = {Biomimetics (Basel, Switzerland)},
year = {2026},
month = aug,
volume = {11},
number = {8},
pages = {569},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2313-7673},
doi = {10.3390/
url = {https://
pmid = {42645286},
pmcid = {PMC13510150}
}
RIS
TY - JOUR
AU - Bu, Xiangdong
AU - Jiang, Hongru
AU - Guo, Tianruo
AU - Li, Heng
AU - Chen, Yao
TI - Pretraining of Embodied Recurrent Networks Bridges the Gap Between Artificial and Cortical Neural Activities
T2 - Biomimetics (Basel, Switzerland)
J2 - Biomimetics (Basel)
PY - 2026
DA - 2026/
VL - 11
IS - 8
SP - 569
SN - 2313-7673
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.3390/
"type": "article-journal",
"title": "Pretraining of Embodied Recurrent Networks Bridges the Gap Between Artificial and Cortical Neural Activities",
"container-title": "Biomimetics (Basel, Switzerland)",
"author": [
{
"family": "Bu",
"given": "Xiangdong"
},
{
"family": "Jiang",
"given": "Hongru"
},
{
"family": "Guo",
"given": "Tianruo"
},
{
"family": "Li",
"given": "Heng"
},
{
"family": "Chen",
"given": "Yao"
}
],
"container-title-short":
"volume": "11",
"issue": "8",
"page": "569",
"DOI": "10.3390/
"PMID": "42645286",
"PMCID": "PMC13510150",
"ISSN": "2313-7673",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
9
]
]
}
}
The tracing map gets a citation of its own once an author has validated it and it has a DOI.
Similar papers
The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.
- [1] doi:10.1038/s41467-024-48008-7 [code]
- De novo motor learning creates structure in neural activity that shapes adaptation.Journal: Nature communicationsIn common: PyTorch, scikit-learn, SciPy, 2 other tools, systems, 14 references
- [2] doi:10.7554/elife.93060 [code]
- Aligned and oblique dynamics in recurrent neural networks.Journal: eLifeIn common: PyTorch, scikit-learn, SciPy, 2 other tools, 14 references
- [3] doi:10.1038/s41467-024-51308-7 [code]
- Reach-dependent reorientation of rotational dynamics in motor cortex.Journal: Nature communicationsIn common: systems, 13 references
- [4] doi:10.1371/journal.pcbi.1011954 [code]
- Emergent neural dynamics and geometry for generalization in a transitive inference task.Journal: PLoS computational biologyIn common: PyTorch, scikit-learn, SciPy, 2 other tools, 11 references
- [5] doi:10.1038/s41467-025-58421-1 [code]
- Continuous sensorimotor transformation enhances robustness of neural dynamics to perturbation in macaque motor cortex.Journal: Nature communicationsIn common: SciPy, Matplotlib, NumPy, systems, 11 references
- [6] doi:10.1371/journal.pcbi.1011852 [code]
- Trained recurrent neural networks develop phase-locked limit cycles in a working memory task.Journal: PLoS computational biologyIn common: PyTorch, scikit-learn, SciPy, 2 other tools, 10 references
- [7] doi:10.1073/pnas.2212887121 [code]
- Modeling and dissociation of intrinsic and input-driven neural population dynamics underlying behavior.Journal: Proceedings of the National Academy of Sciences of the United States of AmericaIn common: scikit-learn, SciPy, Matplotlib, 1 other tool, systems, 10 references
- [8] doi:10.1523/jneurosci.1777-23.2024 [code]
- Motor Cortex Latent Dynamics Encode Spatial and Temporal Arm Movement Parameters Independently.Journal: The Journal of neuroscience : the official journal of the Society for NeuroscienceIn common: systems, 11 references
- [9] doi:10.1016/j.neuron.2026.07.016 [code]
- Inferring brain-wide interactions using data-constrained recurrent neural network models.Journal: NeuronIn common: Matplotlib, NumPy, systems, 10 references
- [10] doi:10.1038/s41586-023-06714-0 [code]
- Preserved neural dynamics across animals performing similar behaviour.Journal: NatureIn common: scikit-learn, SciPy, Matplotlib, 1 other tool, systems, 10 references
Contribute
The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.
Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.
Claim this paper
Correct its record
Say what each link of this record is, remove the ones that are not the paper's, add the ones that are missing. The correction becomes a new version of the record, in its Versions section.
Validate its tracing map
You validate the map as this page shows it: 1 repository of the authors' code, each at its verified commit and with its license, 34 scripts, and 8 matches between paragraphs and code (see the Code and Map sections). It then receives a DOI on Zenodo, with you (your ORCID iD) and OSCR as its creators; the code itself is not deposited.
The map's fingerprint: sha256:01e7a06ba916f3dc…
Add the badge to the code's README
If you are an author or a maintainer of this paper's code, you can add this badge. It says what OSCR knows of the paper (its code, its validated tracing map) and links the code to this page. Paste one of these snippets under the README's title. Keep the two marks around it, so that the badge can be replaced in place and is never added twice. OSCR changes nothing in your repository.
Markdown
<!-- oscr-badge:start -->
[](https://openscicode.org/badge/doi/10.3390/biomimetics11080569)
<!-- oscr-badge:end -->reStructuredText
.. oscr-badge:start
.. image:: https://openscicode.org/badge/doi/10.3390/biomimetics11080569.svg
:target: https://openscicode.org/badge/doi/10.3390/biomimetics11080569
:alt: OSCR
.. oscr-badge:endHTML
<!-- oscr-badge:start -->
<a href="https://openscicode.org/badge/doi/10.3390/biomimetics11080569"><img src="https://openscicode.org/badge/doi/10.3390/biomimetics11080569.svg" alt="OSCR"></a>
<!-- oscr-badge:end -->On GitHub, open the README, choose Edit (the pencil), paste the snippet under the title, then "Commit changes".
If you choose to, you can have the badge kept up to date for you, with oscr badge --write from the command line or with the GitHub Action in your repository's workflows. Every other form and option (a card, AsciiDoc, LaTeX, shields.io) is on the badge page.
Request its removal
To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).
Discussion, reproductions, activity
Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.
Report a mismatch between the code and the paper · Report a code error (signed in)
Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.
Report a reproduction failure (signed in)
Versions of its code: the releases of its code tied to a version of this paper (the preprint, the accepted manuscript, the version of record…), each with the tracing map versioned with it.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.
