Cerebellum-inspired neural network of supervised learning with tensor-based sparse coding for multi-class classification.
Paper
Loaded from Europe PMC by your browser, not stored by OSCR: doi.org · Europe PMC
The paper is loaded when this pane is shown.
The authors' code
Python · 20 lines · 485 B · MIT
- import threading
- from benchmark.runner import JobManager
- from configs import LOGGER
- from utils.argparser import get_args_cli
- from utils.helper import UploadS3Thread
- def start_s3_sync():
- stop_flag = threading.Event()
- upload_s3_thread = UploadS3Thread(stop_flag)
- upload_s3_thread.start()
- if __name__ == "__main__":
- arg_dict = get_args_cli()
- LOGGER.info('received task with args: %s' % arg_dict)
- start_s3_sync()
- jm = JobManager(**arg_dict)
- jm.start()
app.py at commit b2617bb, under MIT · at the source
Overview
- School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China
- Institute of Natural Sciences, Shanghai Jiao Tong University, Shanghai, China
- Ministry of Education Key Laboratory of Scientific and Engineering Computing, Shanghai Jiao Tong University, Shanghai, China
- Shanghai Frontier Science Center of Modern Analysis, Shanghai Jiao Tong University, Shanghai, China
- State Key Laboratory of Synergistic Chem-Bio Synthesis, Shanghai Jiao Tong University, Shanghai, China
Abstract
Under the Marr-Ito-Albus framework, the cerebellum performs supervised learning in Purkinje cells upon the unsupervised sparse representations generated within granule cells, contributing fundamentally to associative learning in motor control. However, the specific mechanisms through which cerebellar circuitry and plasticity rules enable supervised learning, and properties of the sparse coding induced by cerebellar architectural constraints, remain poorly characterized. To address this, we first established a sparse coding mechanism inspired by anatomical and physiological properties of the granular layer, including input-sharing connectivity from mossy fibers, Golgi-cell-mediated localized feedback inhibition for winner-take-all sparsification, and activity-dependent bias adjustments. This sparse coding, implemented via efficient tensor-based computations, preserves local neighborhood structures as revealed in a geometric interpretation. Furthermore, we demonstrated that error signals transmitted via climbing fibers to Purkinje cells, integrated with intrinsic plasticity, drive efficient learning of the sparse representations for multi-class classification, leading to accurate population coding for judgments in the cerebellar nuclei. The resultant cerebellum-inspired neural network model achieved a test accuracy of 90.50±0.10% on Fashion-MNIST, performance comparable to a backpropagation-trained single-hidden-layer feedforward neural network, while providing more than 5× computational acceleration. The model further exhibited proof-of-principle closed-loop control capability in simplified motor tasks, including balancing a cart-attached pole and controlling a robotic arm to reach targets. Our study delineates cerebellum-inspired sparse coding and supervised learning mechanisms, and demonstrates robust performance of the cerebellum-inspired neural network across multiple task domains. These results suggest that cerebellum-inspired architectures would provide useful design principles for lightweight neural networks in resource-limited and latency-critical applications.
Reproduced under the paper's license (CC BY), from the paper cited above.
Repositories
Its files are read in the Code ↔ Paper reader above.
runguangzhou/Cerebellum-inspired-neural-network
35e8953c429df01ca5bb7746a90d4269c49066c8, 7 August 2026Availability: 1 check, the latest on 27 September 2026: the link answers
- 27 September 2026: the link answers
1 file, not copied: shown from their source
OSCR keeps no copy of these files: this repository has no license that allows it. The reader above shows each one from its source, fetched by your browser at commit 35e8953, when its fingerprint is the one OSCR verified. How this works.
- README.md — Text, 4 lines, shown from its source
zalandoresearch/fashion-mnist
b2617bb6d3ffa2e429640350f613e3291e10b141, 21 March 2022Availability: 1 check, the latest on 27 September 2026: the link answers
- 27 September 2026: the link answers
14 files
- app.py — Python, 20 lines
- benchmark/
__init__.py — Python, 1 line - benchmark/
convnet.py — Python, 149 lines - benchmark/
runner.py — Python, 207 lines - configs.py — Python, 90 lines
- static/
js/ — JavaScript, 118 linesvue-binding.js - utils/
__init__.py — Python, 1 line - utils/
argparser.py — Python, 39 lines - utils/
helper.py — Python, 84 lines - utils/
mnist_reader.py — Python, 22 lines - visualization/
__init__.py — Python, 1 line - visualization/
project_zalando.py — Python, 43 lines - LICENSE — License, 7 lines
- README.md — Text, 283 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:
- 2 repositories of the authors' code, each at its verified commit, with its license and how the link was found in the paper;
- 12 scripts, each with its path and the digest of its content;
- no match between paragraphs and code yet;
- 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
No dataset and no data link were found in the paper.
Data Availability
All code used for modeling and plotting is available on a GitHub repository at 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, 4 authors, 9 MeSH terms, 4 funders, 56 references.
Cite
This paper
Zhou, R., Zhou, D., Li, S., & Chen, X. (2026). Cerebellum-inspired neural network of supervised learning with tensor-based sparse coding for multi-class classification. PLoS computational biology, 22(8), e1014595. https://
BibTeX
@article{zhou2026cerebel
author = {Zhou, Runguang and Zhou, Douglas and Li, Songting and Chen, Xiaoyu},
title = {{Cerebellum-inspired neural network of supervised learning with tensor-based sparse coding for multi-class classification}},
journal = {PLoS computational biology},
year = {2026},
month = aug,
volume = {22},
number = {8},
pages = {e1014595},
publisher = {PLOS},
issn = {1553-734X},
doi = {10.1371/
url = {https://
pmid = {42611851},
pmcid = {PMC13485046}
}
RIS
TY - JOUR
AU - Zhou, Runguang
AU - Zhou, Douglas
AU - Li, Songting
AU - Chen, Xiaoyu
TI - Cerebellum-inspired neural network of supervised learning with tensor-based sparse coding for multi-class classification
T2 - PLoS computational biology
J2 - PLoS Comput Biol
PY - 2026
DA - 2026/
VL - 22
IS - 8
SP - e1014595
SN - 1553-734X
PB - PLOS
DO - 10.1371/
UR - https://
LA - en
ER -
CSL-JSON
{
"id": "10.1371/
"type": "article-journal",
"title": "Cerebellum-inspired neural network of supervised learning with tensor-based sparse coding for multi-class classification",
"container-title": "PLoS computational biology",
"author": [
{
"family": "Zhou",
"given": "Runguang"
},
{
"family": "Zhou",
"given": "Douglas"
},
{
"family": "Li",
"given": "Songting"
},
{
"family": "Chen",
"given": "Xiaoyu"
}
],
"container-title-short":
"volume": "22",
"issue": "8",
"page": "e1014595",
"DOI": "10.1371/
"PMID": "42611851",
"PMCID": "PMC13485046",
"ISSN": "1553-734X",
"publisher": "PLOS",
"URL": "https://
"language": "en",
"issued": {
"date-parts": [
[
2026,
8,
18
]
]
}
}
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:10.1073/pnas.2616911123 [code]
- Cerebellar microcircuits enable robust evidence-based decisions through cortico-cerebellar coupling.Journal: Proceedings of the National Academy of Sciences of the United States of AmericaIn common: Matplotlib, NumPy, 6 references
- [2] doi:10.1038/s41467-026-75371-4 [code]
- Cerebellar neural populations orchestrate dopamine reward signaling with single-trial precision.Journal: Nature communicationsIn common: TensorFlow, scikit-learn, Matplotlib, 1 other tool, systems, 2 references
- [3] doi:10.1038/s41593-026-02255-7 [code]
- Neural circuits encode prior knowledge of temporal statistics.Journal: Nature neuroscienceIn common: scikit-learn, Matplotlib, NumPy, systems, 3 references
- [4] doi:10.3389/fnsys.2026.1822122 [code]
- Convergence-divergence circuits for multimodal integration of innate and learned opponent valences.Journal: Frontiers in systems neuroscienceIn common: TensorFlow, scikit-learn, Matplotlib, 1 other tool, systems, 1 reference
- [5] doi:10.1038/s41467-026-76878-6 [code]
- Temporal coding enables hyperacuity in event-based vision.Journal: Nature communicationsIn common: TensorFlow, scikit-learn, Matplotlib, 1 other tool, 1 reference
- [6] doi:10.1038/s41467-026-74460-8 [code]
- Spike-based alignment learning solves the weight transport problem.Journal: Nature communicationsIn common: TensorFlow, scikit-learn, Matplotlib, 1 other tool, 1 reference
- [7] doi:10.1038/s41467-026-76109-y [code]
- Assistive algorithms influence neural representations in motor brain-computer interfaces.Journal: Nature communicationsIn common: scikit-learn, Matplotlib, NumPy, systems, 1 reference
- [8] doi:10.1126/sciadv.aed6417 [code]
- Intrinsic timing, not temporal prediction, underlies ramping dynamics in visual and parietal cortex during passive behavior.Journal: Science advancesIn common: scikit-learn, Matplotlib, NumPy, systems, 1 reference
- [9] doi:10.1371/journal.pbio.3003831 [code]
- Disinhibitory signaling enables flexible coding of top-down information in cortical networks.Journal: PLoS biologyIn common: TensorFlow, scikit-learn, Matplotlib, 1 other tool, systems
- [10] doi:10.1038/s41467-026-73999-w [code]
- Independence and coherence in temporal sequence computation across the fronto-parietal network.Journal: Nature communicationsIn common: TensorFlow, scikit-learn, Matplotlib, 1 other tool, systems
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: 2 repositories of the authors' code, each at its verified commit and with its license, 12 scripts, and 0 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: sha256:87fe4e8cf6ce753c…
Add the badge to its README
The badge links the code to this page. Copy one of these into the README of the paper's code: only you decide where it goes, and nothing is changed for you.
Markdown
[, paste the snippet at the top, then “Commit changes…” and, to review it first, “Create a new branch and start a pull request”. You open the pull request; OSCR asks for no permission.
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: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.
Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.
Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.