Diverse deep neural networks all predict human IT well, after training and fitting
Open accessPreprint — published as 10.1162/jocn_a_01755
The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.
Abstract
Deep neural networks (DNNs) trained on object recognition provide the best current models of high-level visual areas in the brain. What remains unclear is how strongly network design choices, such as architecture, task training, and subsequent fitting to brain data contribute to the observed similarities. Here we compare a diverse set of nine DNN architectures on their ability to explain the representational geometry of 62 isolated object images in human inferior temporal (hIT) cortex, as measured with functional magnetic resonance imaging. We compare untrained networks to their task-trained counterparts, and assess the effect of fitting them to hIT using a cross-validation procedure. To best explain hIT, we fit a weighted combination of the principal components of the features within each layer, and subsequently a weighted combination of layers. We test all models across all stages of training and fitting for their correlation with the hIT representational dissimilarity matrix (RDM) using an independent set of images and subjects. We find that trained models significantly outperform untrained models (accounting for 57% more of the explainable variance), suggesting that features representing natural images are important for explaining hIT. Model fitting further improves the alignment of DNN and hIT representations (by 124%), suggesting that the relative prevalence of different features in hIT does not readily emerge from the particular ImageNet object-recognition task used to train the networks. Finally, all DNN architectures tested achieved equivalent high performance once trained and fitted. Similar ability to explain hIT representations appears to be shared among deep feedforward hierarchies of nonlinear features with spatially restricted receptive fields.
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 classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Representational similarity analysis-connecting the branches of systems neuroscience
Kriegeskorte, N. (2008) · Frontiers in Systems Neuroscience · doi:10.3389/neuro.06.004.2008 · Cited by 3,355
Self-citationEquivalence Tests: A Practical Primer for t Tests, Correlations, and Meta-Analyses
Lakens, D. (2017) · Social Psychological and Personality Science · doi:10.1177/1948550617697177 · Cited by 3,001 · cited 5×
“For each pair of models, we tested whether the observed differences between the hIT correlation of the two models, across bootstrap samples, were significantly larger than the lower bound of the 95% confidence interval on noise ceiling variation and, at the same time, significantly lower than the upper bound of the co…”
BackgroundMethodInfluentialShortcut learning in deep neural networks
Geirhos, R., Jacobsen, J.-H., Michaelis, C., Zemel, R., Brendel, W., Bethge, M., & Wichmann, F. A. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00257-z · Cited by 2,224
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
Using goal-driven deep learning models to understand sensory cortex
Yamins, D. L. K., & DiCarlo, J. J. (2016) · Nature Neuroscience · doi:10.1038/nn.4244 · Cited by 1,621
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F. A., & Brendel, W. (2018) · arXiv · doi:10.48550/arxiv.1811.12231 · Cited by 1,490
Deep 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
Self-citationA deep learning framework for neuroscience
Richards, B. A., Lillicrap, T. P., Beaudoin, P., Bengio, Y., Bogacz, R., Christensen, A., Clopath, C., Costa, R. P., de Berker, A., Ganguli, S., et al. (2019) · Nature Neuroscience · doi:10.1038/s41593-019-0520-2 · Cited by 1,027 · cited 2×
“Going forward, deep learning models in visual neuroscience will more broadly explore the space of objective functions, learning rules, architectures (Richards et al., 2019), and training diets (Mehrer et al., 2017).”
BackgroundSelf-citation
Cited by
Conwell, C., Prince, J. S., Kay, K. N., Alvarez, G. A., & Konkle, T. (2022) · doi:10.1101/2022.03.28.485868 · Cited by 160
Performance vs. competence in human–machine comparisons
Firestone, C. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1905334117 · Cited by 150
An ecologically motivated image dataset for deep learning yields better models of human vision
Mehrer, J., Spoerer, C. J., Jones, E. C., Kriegeskorte, N., & Kietzmann, T. C. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2011417118 · Cited by 140
Self-citationIndividual differences among deep neural network models
Mehrer, J., Spoerer, C. J., Kriegeskorte, N., & Kietzmann, T. C. (2020) · Nature Communications · doi:10.1038/s41467-020-19632-w · Cited by 133
Self-citationConwell, C., Prince, J. S., Kay, K. N., Alvarez, G. A., & Konkle, T. (2024) · Nature Communications · doi:10.1038/s41467-024-53147-y · Cited by 100
Metadata
- Authors
- Storrs, K. R., Kietzmann, T. C., Walther, A., Mehrer, J., & Kriegeskorte, N.
- Venue
- bioRxiv (Cold Spring Harbor Laboratory)
- Publisher
- openRxiv
- Published
- 2020-05-08
- OpenAlex
- W3023717326
- Cited by
- 25
- References
- 19
- 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: Diverse deep neural networks all predict human IT well, after training and fitting. https://app.cochat.ai/papers/10.1101/2020.05.07.082743
- The paper
- Storrs, K. R., Kietzmann, T. C., Walther, A., Mehrer, J., & Kriegeskorte, N. (2020). Diverse deep neural networks all predict human IT well, after training and fitting. bioRxiv (Cold Spring Harbor Laboratory). https://doi.org/10.1101/2020.05.07.082743
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.