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
Items 201–225 of 225
Taylor, N. L., D’Souza, A., Munn, B., Lv, J., Záborszky, L., Müller, E. J., Wainstein, G., Calamante, F., & Shine, J. M. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.119455 · Cited by 42
Inhibitory top-down projections from zona incerta mediate neocortical memory
Schroeder, A., Pardi, M. B., Keijser, J., Dalmay, T., Groisman, A. I., Schuman, E. M., Sprekeler, H., & Letzkus, J. J. (2023) · Neuron · doi:10.1016/j.neuron.2022.12.010 · Cited by 41
Red nucleus connectivity as revealed by constrained spherical deconvolution tractography
Milardi, D., Cacciola, A., Cutroneo, G., Marino, S., Irrera, M., Cacciola, G., Santoro, G., Ciolli, P., Anastasi, G., Calabrò, R. S., et al. (2016) · Neuroscience Letters · doi:10.1016/j.neulet.2016.05.009 · Cited by 39
A Thalamic Orphan Receptor Drives Variability in Short-Term Memory
Hsiao, K., Noble, C., Pitman, W. A., Yadav, N., Kumar, S., Keele, G. R., Terceros, A. A., Kanke, M., Conniff, T., Cheleuitte-Nieves, C., et al. (2020) · Cell · doi:10.1016/j.cell.2020.09.011 · Cited by 38
Cortical glutamatergic projection neuron types contribute to distinct functional subnetworks
Mohan, H., An, X., Xu, X. H., Kondo, H., Zhao, S., Matho, K. S., Wang, B., Musall, S., Mitra, P. P., & Huang, Z. J. (2023) · Nature Neuroscience · doi:10.1038/s41593-022-01244-w · Cited by 38
Neglect of contralateral visual stimuli in monkeys with unilateral striatal dopamine depletion
Apicella, P., Legallet, E., Nieoullon, A. L., & Trouche, E. (1991) · Behavioural Brain Research · doi:10.1016/s0166-4328(05)80112-3 · Cited by 37
Feature selectivity can explain mismatch signals in mouse visual cortex
Muzzu, T., & Saleem, A. B. (2021) · Cell Reports · doi:10.1016/j.celrep.2021.109772 · Cited by 37
Brenner, J. M., Beltramo, R., Gerfen, C. R., Ruediger, S., & Scanziani, M. (2023) · Neuron · doi:10.1016/j.neuron.2023.04.022 · Cited by 33
Park, J. M., Hong, Y. K., Rodgers, C. C., Dahan, J. B., Harano, N., Schmidt, E. R. E., & Bruno, R. M. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.08.12.245381 · Cited by 30
Ruediger, S., & Scanziani, M. (2020) · eLife · doi:10.7554/elife.59247 · Cited by 30
Pyramidal cell types drive functionally distinct cortical activity patterns during decision-makingPreprint
Musall, S., Sun, X. R., Mohan, H., An, X., Gluf, S., Li, S.-J., Drewes, R., Cravo, E., Lenzi, I., Yin, C., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.09.27.461599 · Cited by 26
(2022) · Cambridge University Press eBooks · doi:10.1017/9781108674287 · Cited by 26
Dora, S., Bohte, S. M., & Pennartz, C. M. A. (2021) · Frontiers in Computational Neuroscience · doi:10.3389/fncom.2021.666131 · Cited by 24
Self-citationFitting predictive coding to the neurophysiological data
Spratling, M. W. (2019) · Brain Research · doi:10.1016/j.brainres.2019.146313 · Cited by 23
Thalamocortical contribution to flexible learning in neural systems
Wang, M. B., & Halassa, M. M. (2022) · Network Neuroscience · doi:10.1162/netn_a_00235 · Cited by 23
Cortical glutamatergic projection neuron types contribute to distinct functional subnetworksPreprint
Mohan, H., An, X., Xu, X. H., et al. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.12.30.474537 · Cited by 19
Molnár, Z., & Rockland, K. S. (2020) · Elsevier eBooks · doi:10.1016/b978-0-12-814411-4.00005-6 · Cited by 18
Three learning stages and accuracy–efficiency tradeoff of restricted Boltzmann machines
Dabelow, L., & Ueda, M. (2022) · Nature Communications · doi:10.1038/s41467-022-33126-x · Cited by 14
Burkhalter, A., D’Souza, R. D., Ji, W., & Meier, A. M. (2023) · Annual Review of Neuroscience · doi:10.1146/annurev-neuro-083122-021241 · Cited by 13
The Rough Seas of Cortical Cartography
Zeki, S. (2018) · Trends in Neurosciences · doi:10.1016/j.tins.2018.03.005 · Cited by 12
Thalamus drives active dendritic computations in cortexPreprint
Bast, A., Guest, J. M., Fruengel, R., Narayanan, R. T., de Kock, C. P. J., & Oberlaender, M. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.10.21.465325 · Cited by 12
Defying Expectations: How Neurons Compute Prediction Errors in Visual Cortex
Padamsey, Z., & Rochefort, N. L. (2020) · Neuron · doi:10.1016/j.neuron.2020.12.005 · Cited by 8
Gaussian-Bernoulli RBMs Without TearsPreprint
Liao, R., Kornblith, S., Ren, M., Fleet, D. J., & Hinton, G. E. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2210.10318 · Cited by 7
Smythies, J. (2015) · Frontiers in Cellular Neuroscience · doi:10.3389/fncel.2015.00443 · Cited by 5
Footshock-Induced Activation of the Claustrum-Entorhinal Cortical Pathway in Freely Moving Mice
HUANG, W., QIN, J., Zhang, C., Qin, H., & Xie, P. (2022) · Physiological Research · doi:10.33549/physiolres.934899 · Cited by 5
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
