Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream
Open accessThe DOI matches its Crossref record; 11 of the 11 references it cites were found in a registry or an index.
Abstract
After training on large datasets, certain deep neural networks are surprisingly good models of the neural mechanisms of adult primate visual object recognition. Nevertheless, these models are poor models of the development of the visual system because they posit millions of sequential, precisely coordinated synaptic updates, each based on a labeled image. While ongoing research is pursuing the use of unsupervised proxies for labels, we here explore a complementary strategy of reducing the required number of supervised synaptic updates to produce an adult-like ventral visual stream (as judged by the match to V1, V2, V4, IT, and behavior). Such models might require less precise machinery and energy expenditure to coordinate these updates and would thus move us closer to viable neuroscientific hypotheses about how the visual system wires itself up. Relative to the current leading model of the adult ventral stream, we here demonstrate that the total number of supervised weight updates can be substantially reduced using three complementary strategies: First, we find that only 2% of supervised updates (epochs and images) are needed to achieve ~80% of the match to adult ventral stream. Second, by improving the random distribution of synaptic connectivity, we find that 54% of the brain match can already be achieved “at birth” (i.e. no training at all). Third, we find that, by training only ~5% of model synapses, we can still achieve nearly 80% of the match to the ventral stream. When these three strategies are applied in combination, we find that these new models achieve ~80% of a fully trained model’s match to the brain, while using two orders of magnitude fewer supervised synaptic updates. These results reflect first steps in modeling not just primate adult visual processing during inference, but also how the ventral visual stream might be “wired up” by evolution (a model’s “birth” state) and by developmental learning (a model’s updates based on visual experience).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Performance-optimized hierarchical models predict neural responses in higher visual cortex
Yamins, D. L. K., Hong, H., Cadieu, C. F., Solomon, E. A., Seibert, D., & DiCarlo, J. J. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1403112111 · Cited by 1,924
Self-citationCompetitive learning: From interactive activation to adaptive resonance
Grossberg, S. (1987) · Cognitive Science · doi:10.1111/j.1551-6708.1987.tb00862.x · Cited by 1,471 · cited 1×
“biological, among others due to the propagation of gradients [41–43].”
BackgroundDeep supervised, but not unsupervised, models may explain IT cortical representation
Khaligh-Razavi, S.-M., & Kriegeskorte, N. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003915 · Cited by 1,204
Data-Efficient Image Recognition with Contrastive Predictive Coding
Hénaff, O. J., Srinivas, A., De Fauw, J., Razavi, A., Doersch, C., Eslami, S. M. A., & Oord, A. V. D. (2019) · arXiv · doi:10.48550/arxiv.1905.09272 · Cited by 1,014
Rethinking Few-Shot Image Classification: A Good Embedding is All You Need?
Tian, Y., Wang, Y., Krishnan, D., Tenenbaum, J. B., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58568-6_16 · Cited by 952
Mechanisms underlying development of visual maps and receptive fields
Huberman, A. D., Feller, M. B., & Chapman, B. (2008) · Annual Review of Neuroscience · doi:10.1146/annurev.neuro.31.060407.125533 · Cited by 628 · cited 2×
“For example, we know that there are multiple neuro-developmental mechanisms, such as sponta-neous retinal waves and axon guidance cues, that significantly shape the architecture and function of the visual system requiring no (or very little) visual experience ((Huberman et al., 2008)).”
BackgroundTheories of Error Back-Propagation in the Brain
Whittington, J. C. R., & Bogacz, R. (2019) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2018.12.005 · Cited by 420 · cited 2×
“biological, among others due to the propagation of gradients [41–43].”
BackgroundOn the importance of single directions for generalization
Morcos, A. S., Barrett, D. G. T., Rabinowitz, N. C., & Botvinick, M. (2018) · arXiv · doi:10.48550/arxiv.1803.06959 · Cited by 305
Cited by
The neural architecture of language: Integrative modeling converges on predictive processing
Schrimpf, M., Blank, I. A., Tuckute, G., Kauf, C., Hosseini, E. A., Kanwisher, N., Tenenbaum, J. B., & Fedorenko, E. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2105646118 · Cited by 517
Self-citationThe neural architecture of language: Integrative modeling converges on predictive processing
(2020) · doi:10.1101/2020.06.26.174482 · Cited by 129
Hosseini, E. A., Schrimpf, M., Zhang, Y., Bowman, S., Zaslavsky, N., & Fedorenko, E. (2024) · Neurobiology of Language · doi:10.1162/nol_a_00137 · Cited by 63
“Prior work in vision (Geiger et al., 2020; Storrs et al., 2021) has suggested that training affects model performance differently across layers, with early layers already reaching close to maximal performance with a limited amount of training, but later layers continuing to benefit from…”
BackgroundResultInfluentialSelf-citationBuilding transformers from neurons and astrocytes
(2023) · doi:10.1073/pnas.2219150120 · Cited by 57
Metadata
- Authors
- Geiger, F., Schrimpf, M., Marques, T., & DiCarlo, J. J.
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2020-06-08
- OpenAlex
- W3033502539
- Cited by
- 10
- References
- 11
- Type
- posted content
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream. https://app.cochat.ai/papers/10.1101/2020.06.08.140111
- The paper
- Geiger, F., Schrimpf, M., Marques, T., & DiCarlo, J. J. (2020). Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.1101/2020.06.08.140111
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.