The DOI matches its Crossref record; 225 of the 225 references it cites were found in a registry or an index.
How deep is the brain? The shallow brain hypothesis
Open accessAbstract
Deep learning and predictive coding architectures commonly assume that inference in neural networks is hierarchical. However, largely neglected in deep learning and predictive coding architectures is the neurobiological evidence that all hierarchical cortical areas, higher or lower, project to and receive signals directly from subcortical areas. Given these neuroanatomical facts, today's dominance of cortico-centric, hierarchical architectures in deep learning and predictive coding networks is highly questionable; such architectures are likely to be missing essential computational principles the brain uses. In this Perspective, we present the shallow brain hypothesis: hierarchical cortical processing is integrated with a massively parallel process to which subcortical areas substantially contribute. This shallow architecture exploits the computational capacity of cortical microcircuits and thalamo-cortical loops that are not included in typical hierarchical deep learning and predictive coding networks. We argue that the shallow brain architecture provides several critical benefits over deep hierarchical structures and a more complete depiction of how mammalian brains achieve fast and flexible computational capabilities.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In the typical mammalian brain, however, recurrent loops between the subcortex and regions of the cortex are a vital and almost universal feature of processing [85].”
From Phenomenal interface theory: a model for basal consciousness (2025) · cites this paper as [85]
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex
Hubel, D. H., & Wiesel, T. N. (1962) · The Journal of Physiology · doi:10.1113/jphysiol.1962.sp006837 · Cited by 13,680
An Integrative Theory of Prefrontal Cortex Function
Miller, E. K., & Cohen, J. D. (2001) · Annual Review of Neuroscience · doi:10.1146/annurev.neuro.24.1.167 · Cited by 12,803
Parallel organization of functionally segregated circuits linking basal ganglia and cortex
Alexander, G. E., DeLong, M. R., & Strick, P. L. (1986) · Annual Review of Neuroscience · doi:10.1146/annurev.ne.09.030186.002041 · Cited by 8,527
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
The free-energy principle: a unified brain theory?
Friston, K. (2010) · Nature Reviews Neuroscience · doi:10.1038/nrn2787 · Cited by 8,120 · cited 1×
“This idea of hierarchical Bayesian inference has been the dominant framework in neuroscience over the last decade 17,40–43 .”
BackgroundA robust layered control system for a mobile robot
Brooks, R. (1986) · IEEE Journal on Robotics and Automation · doi:10.1109/jra.1986.1087032 · Cited by 7,799 · cited 2×
“Although the cortical hierarchy is useful for representing abstract features in their context, we propose a processing regime, the shallow brain hypothesis, whereby the entire cortex is essentially one giant layer providing contextualized input to subcortical motor and premotor centres in the…”
BackgroundDistributed hierarchical processing in the primate cerebral cortex
Felleman, D. J., & Van Essen, D. C. (1991) · Cerebral Cortex · doi:10.1093/cercor/1.1.1 · Cited by 7,783
Research works printed but not linked: 6
- Minsky, M. & Papert, S. Perceptrons; An Introduction to Computational Geometry (MIT Press, 1969).
- Cohen, N., Sharir, O. & Shashua, A. On the expressive power of deep learning: a tensor analysis. In 29th Annual Conference on Learning Theory (eds. Feldman, V., Rakhlin, A. & Shamir, O.) 698–728 (2016).
- Von Neumann, J. The Computer and the Brain (Yale Univ. Press, 1958).
- Haider, P., Ellenberger, B., Kriener, L., Jordan, J., Senn, W. & Petrovici, M. A. Latent equilibrium: a unified learning theory for arbitrarily fast computation with arbitrarily slow neurons. Adv. Neural Inf. Process. Syst. 34, 17839–17851 (2021).
- Ruis, L., Andreas, J., Baroni, M., Bouchacourt, D. & Lake, B. M. A benchmark for systematic generalization in grounded language understanding. In Proc. 34th Int. Conf. Neural Information Processing Systems (eds. Larochelle, H. et al.) 19861–19872 (Curran, 2020).
- Lake, B. M. & Baroni, M. Generalization without systematicity: on the compositional skills of sequence-to-sequence recurrent networks. In Int. Conf. Machine Learning (eds. Dy, J. & Krause, A.) 2879–2888 (2018).
Cited by
Sorted by citations
An integrative, multiscale view on neural theories of consciousness
Storm, J. F., Klink, P. C., Aru, J., Senn, W., Goebel, R., Pigorini, A., Avanzini, P., Vanduffel, W., Roelfsema, P. R., Massimini, M., et al. (2024) · Neuron · doi:10.1016/j.neuron.2024.02.004 · Cited by 114
“The next aggregate levels are local (within-area) recurrent processing in cortical microcircuits (C, upper left; from Suzuki et al. 138 ) and cortico-thalamic loops (C, HO: higher order).”
Self-citationThe feasibility of artificial consciousness through the lens of neuroscience
Aru, J., Larkum, M. E., & Shine, J. M. (2023) · Trends in Neurosciences · doi:10.1016/j.tins.2023.09.009 · Cited by 98
Self-citationIntelligent nanophotonics: when machine learning sheds light
Wu, N., Sun, Y., Hu, J., Yang, C., Bai, Z., Wang, F. X., Cui, X., He, S., Li, Y., Zhang, C., et al. (2025) · eLight · doi:10.1186/s43593-025-00085-x · Cited by 91
Tononi, G., Boly, M., & Cirelli, C. (2024) · Neuron · doi:10.1016/j.neuron.2024.04.011 · Cited by 70
Brain-inspired artificial intelligence research: A review
Wang, G., Bao, H., Liu, Q., Zhou, T., Wu, S., Huang, T., Yu, Z., Lu, C., Gong, Y., Zhang, Z., et al. (2024) · Science China Technological Sciences · doi:10.1007/s11431-024-2732-9 · Cited by 43
Metadata
- Authors
- Suzuki, M., Pennartz, C. M. A., & Aru, J.
- Affiliations
- University of Amsterdam (NL)
- University of Tartu (EE)
- Corresponding author
- Aru, Jaan
- Venue
- Nature Reviews Neuroscience
- Published
- 2023-10-27
- Volume
- 24
- Issue
- 12
- Pages
- 778-791
- ISSN
- 1471-003X (ISSN-L)
- 1471-0048
- OpenAlex
- W4387996733
- Cited by
- 79
- References
- 224
- Citations by year
- 2026: 21 · 2025: 26 · 2024: 28 · 2023: 4
- FWCI
- 2.97
- Type
- journal article
- Language
- en
- Open access
- green
- handle.uba.uva.nl
- Licence
- Locations
- Nature reviews. Neuroscience (publishedVersion)
- PubMed (publishedVersion)
- UvA-DARE (University of Amsterdam) (publishedVersion, other-oa)
- Funders
- Brain Science Foundation
- European Commission (HORIZON2020, 945539)
- Eesti Teadusagentuur (PSG728)
- Topics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Neural dynamics and brain function
- Life Sciences › Neuroscience › Cognitive Neuroscience › Memory and Neural Mechanisms
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- thalamocortical loop, cortical microcircuits, predictive coding, deep learning architectures, neural network architecture, massively parallel computing
- MeSH terms
- Animals, Brain, Humans, Mammals, Neural Networks, Computer
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
