No CrossRef data available.
Article contents
Deep neural networks are not a single hypothesis but a language for expressing computational hypotheses
Published online by Cambridge University Press: 06 December 2023
Abstract
An ideal vision model accounts for behavior and neurophysiology in both naturalistic conditions and designed lab experiments. Unlike psychological theories, artificial neural networks (ANNs) actually perform visual tasks and generate testable predictions for arbitrary inputs. These advantages enable ANNs to engage the entire spectrum of the evidence. Failures of particular models drive progress in a vibrant ANN research program of human vision.
- Type
- Open Peer Commentary
- Information
- Copyright
- Copyright © The Author(s), 2023. Published by Cambridge University Press
References
Bashivan, P., Kar, K., & DiCarlo, J. J. (2019). Neural population control via deep image synthesis. Science (New York, N.Y.), 364(6439), eaav9436. https://doi.org/10.1126/science.aav9436CrossRefGoogle ScholarPubMed
Cichy, R. M., Roig, G., & Oliva, A. (2019). The Algonauts project. Nature Machine Intelligence, 1(12), 613–613. https://doi.org/10.1038/s42256-019-0127-zCrossRefGoogle Scholar
Cohen, J., Rosenfeld, E., & Kolter, Z. (2019). Certified adversarial robustness via randomized smoothing. In Chaudhuri, K. & Salakhutdinov, R. (Eds.), Proceedings of the 36th international conference on machine learning. Proceedings of Machine Learning Research, Long Beach, CA, USA (Vol. 97, pp. 1310–1320). https://proceedings.mlr.press/v97/cohen19c.htmlGoogle Scholar
Doerig, A., Sommers, R., Seeliger, K., Richards, B., Ismael, J., Lindsay, G., … Kietzmann, T. C. (2022). The neuroconnectionist research programme. Nature Reviews Neuroscience, 24, 431–450. https://doi.org/10.1038/s41583-023-00705-wCrossRefGoogle Scholar
Dujmović, M., Malhotra, G., & Bowers, J. S. (2020). What do adversarial images tell us about human vision?. eLife, 9, e55978. https://doi.org/10.7554/eLife.55978CrossRefGoogle ScholarPubMed
Dwivedi, K., Bonner, M. F., Cichy, R. M., & Roig, G. (2021). Unveiling functions of the visual cortex using task-specific deep neural networks. PLoS Computational Biology, 17(8), e1009267. https://doi.org/10.1371/journal.pcbi.1009267CrossRefGoogle ScholarPubMed
Feather, J., Durango, A., Gonzalez, R., & McDermott, J. (2019). Metamers of neural networks reveal divergence from human perceptual systems. In Wallach, H., Larochelle, H., Beygelzimer, A., d'Alché-Buc, F., Fox, E., & Garnett, R. (Eds.), Advances in Neural Information Processing Systems, Vancouver, BC, Canada (Vol. 32, pp. 10078–10089). Curran Associates, Inc. https://proceedings.neurips.cc/paper/2019/file/ac27b77292582bc293a51055bfc994ee-Paper.pdfGoogle Scholar
Funahashi, K. I., & Nakamura, Y. (1993). Approximation of dynamical systems by continuous time recurrent neural networks. Neural Networks, 6(6), 801–806. https://doi.org/10.1016/S0893-6080(05)80125-XCrossRefGoogle Scholar
Geirhos, R., Narayanappa, K., Mitzkus, B., Thieringer, T., Bethge, M., Wichmann, F. A., & Brendel, W. (2021). Partial success in closing the gap between human and machine vision. In Ranzato, M., Beygelzimer, A., Dauphin, Y., Liang, P. S., & Wortman Vaughan, J. (Eds.), Advances in Neural Information Processing Systems (Vol. 34, pp. 23885–23899). Curran Associates, Inc. https://proceedings.neurips.cc/paper/2021/file/c8877cff22082a16395a57e97232bb6f-Paper.pdfGoogle Scholar
Geirhos, R., Rubisch, P., Michaelis, C., Bethge, M., Wichmann, F. A., & Brendel, W. (2019). ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In International conference on learning representations, New Orleans, LA, USA. https://openreview.net/forum?id=Bygh9j09KXGoogle Scholar
Golan, T., Raju, P. C., & Kriegeskorte, N. (2020). Controversial stimuli: Pitting neural networks against each other as models of human cognition. Proceedings of the National Academy of Sciences of the United States of America, 117(47), 29330–29337. https://doi.org/10.1073/pnas.1912334117CrossRefGoogle ScholarPubMed
Güçlü, U., & van Gerven, M. A. J. (2015). Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream. Journal of Neuroscience, 35(27), 10005–10014. https://doi.org/10.1523/JNEUROSCI.5023-14.2015CrossRefGoogle ScholarPubMed
Guo, C., Lee, M., Leclerc, G., Dapello, J., Rao, Y., Madry, A., & Dicarlo, J. (2022). Adversarially trained neural representations are already as robust as biological neural representations. In Chaudhuri, K., Jegelka, S., Song, L., Szepesvari, C., Niu, G., & Sabato, S. (Eds.), Proceedings of the 39th international conference on machine learning. Proceedings of Machine Learning Research, Baltimore, MD, USA (Vol. 162, pp. 8072–8081). PMLR. https://proceedings.mlr.press/v162/guo22d.htmlGoogle Scholar
Hermann, K., Chen, T., & Kornblith, S. (2020). The origins and prevalence of texture bias in convolutional neural networks. In Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M. F., & Lin, H. (Eds.), Advances in Neural Information Processing Systems, Vancouver, BC, Canada (Vol. 33, pp. 19000–19015). Curran Associates, Inc. https://proceedings.neurips.cc/paper/2020/file/db5f9f42a7157abe65bb145000b5871a-Paper.pdfGoogle Scholar
Kriegeskorte, N., Mur, M., Ruff, D. A., Kiani, R., Bodurka, J., Esteky, H., … Bandettini, P. A. (2008). Matching categorical object representations in inferior temporal cortex of man and monkey. Neuron, 60(6), 1126–1141. https://doi.org/10.1016/j.neuron.2008.10.043CrossRefGoogle ScholarPubMed
Lindsay, G. W. (2021). Convolutional neural networks as a model of the visual system: Past, present, and future. Journal of Cognitive Neuroscience, 33(10), 2017–2031. https://doi.org/10.1162/jocn_a_01544CrossRefGoogle Scholar
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2019). Towards deep -learning models resistant to adversarial attacks. In International conference on learning representations, Vancouver, BC, Canada. https://openreview.net/forum?id=rJzIBfZAbGoogle Scholar
Newell, A. (1973). You can't play 20 questions with nature and win: Projective comments on the papers of this symposium. In W. G. Chase (Ed.), Visual information processing: Proceedings of the 8th annual Carnegie symposium on cognition, held at the Carnegie-Mellon University, Pittsburgh, Pennsylvania, May 19, 1972 (pp. 283–305). Academic Press.Google Scholar
Nonaka, S., Majima, K., Aoki, S. C., & Kamitani, Y. (2021). Brain hierarchy score: Which deep neural networks are hierarchically brain-like?. iScience, 24(9), 103013. https://doi.org/10.1016/j.isci.2021.103013CrossRefGoogle ScholarPubMed
Nuriel, O., Benaim, S., & Wolf, L. (2021). Permuted AdaIN: Reducing the bias towards global statistics in image classification. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 9482–9491). Online. https://openaccess.thecvf.com/content/CVPR2021/html/Nuriel_Permuted_AdaIN_Reducing_the_Bias_Towards_Global_Statistics_in_Image_CVPR_2021_paper.htmlCrossRefGoogle Scholar
Olshausen, B. A., & Field, D. J. (2005). How close are we to understanding V1?. Neural Computation, 17(8), 1665–1699. https://doi.org/10.1162/0899766054026639CrossRefGoogle ScholarPubMed
Peters, B., & Kriegeskorte, N. (2021). Capturing the objects of vision with neural networks. Nature Human Behaviour, 5(9), 1127–1144. https://doi.org/10.1038/s41562-021-01194-6CrossRefGoogle ScholarPubMed
Rajalingham, R., Issa, E. B., Bashivan, P., Kar, K., Schmidt, K., & DiCarlo, J. J. (2018). Large-scale, high-resolution comparison of the core visual object recognition behavior of humans, monkeys, and state-of-the-art deep artificial neural networks. Journal of Neuroscience, 38(33), 7255–7269. https://doi.org/10.1523/JNEUROSCI.0388-18.2018CrossRefGoogle ScholarPubMed
Rust, N. C., & Movshon, J. A. (2005). In praise of artifice. Nature Neuroscience, 8(12), 1647–1650. https://doi.org/10.1038/nn1606CrossRefGoogle ScholarPubMed
Schäfer, A. M., & Zimmermann, H. G. (2007). Recurrent neural networks are universal approximators. International Journal of Neural Systems, 17(4), 253–263. https://doi.org/10.1142/S0129065707001111CrossRefGoogle ScholarPubMed
Schrimpf, M., Kubilius, J., Hong, H., Majaj, N. J., Rajalingham, R., Issa, E. B., … DiCarlo, J. J. (2018). Brain-Score: Which artificial neural network for object recognition is most brain-like?. BioRxiv, 407007. https://doi.org/10.1101/407007Google Scholar
Serre, T. (2019). Deep learning: The good, the bad, and the ugly. Annual Review of Vision Science, 5, 399–426. https://doi.org/10.1146/annurev-vision-091718-014951CrossRefGoogle ScholarPubMed
Spoerer, C. J., McClure, P., & Kriegeskorte, N. (2017). Recurrent convolutional neural networks: A better model of biological object recognition. Frontiers in Psychology, 8, 1551. https://doi.org/10.3389/fpsyg.2017.01551CrossRefGoogle ScholarPubMed
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013). Intriguing properties of neural networks. arXiv. arXiv:1312.6199. https://doi.org/10.48550/arXiv.1312.6199Google Scholar
Walker, E. Y., Sinz, F. H., Cobos, E., Muhammad, T., Froudarakis, E., Fahey, P. G., … Tolias, A. S. (2019). Inception loops discover what excites neurons most using deep predictive models. Nature Neuroscience, 22(12), 2060–2065. https://doi.org/10.1038/s41593-019-0517-xCrossRefGoogle ScholarPubMed
Target article
Deep problems with neural network models of human vision
Related commentaries (29)
Explananda and explanantia in deep neural network models of neurological network functions
A deep new look at color
Beyond the limitations of any imaginable mechanism: Large language models and psycholinguistics
Comprehensive assessment methods are key to progress in deep learning
Deep neural networks are not a single hypothesis but a language for expressing computational hypotheses
Even deeper problems with neural network models of language
Fixing the problems of deep neural networks will require better training data and learning algorithms
For deep networks, the whole equals the sum of the parts
For human-like models, train on human-like tasks
Going after the bigger picture: Using high-capacity models to understand mind and brain
Implications of capacity-limited, generative models for human vision
Let's move forward: Image-computable models and a common model evaluation scheme are prerequisites for a scientific understanding of human vision
Modelling human vision needs to account for subjective experience
Models of vision need some action
My pet pig won't fly and I want a refund
Neither hype nor gloom do DNNs justice
Neural networks need real-world behavior
Neural networks, AI, and the goals of modeling
Perceptual learning in humans: An active, top-down-guided process
Psychophysics may be the game-changer for deep neural networks (DNNs) to imitate the human vision
Statistical prediction alone cannot identify good models of behavior
The model-resistant richness of human visual experience
The scientific value of explanation and prediction
There is a fundamental, unbridgeable gap between DNNs and the visual cortex
Thinking beyond the ventral stream: Comment on Bowers et al.
Using DNNs to understand the primate vision: A shortcut or a distraction?
Where do the hypotheses come from? Data-driven learning in science and the brain
Why psychologists should embrace rather than abandon DNNs
You can't play 20 questions with nature and win redux
Author response
Clarifying status of DNNs as models of human vision