No CrossRef data available.
Article contents
Psychophysics may be the game-changer for deep neural networks (DNNs) to imitate the human vision
Published online by Cambridge University Press: 06 December 2023
Abstract
Psychologically faithful deep neural networks (DNNs) could be constructed by training with psychophysics data. Moreover, conventional DNNs are mostly monocular vision based, whereas the human brain relies mainly on binocular vision. DNNs developed as smaller vision agent networks associated with fundamental and less intelligent visual activities, can be combined to simulate more intelligent visual activities done by the biological brain.
- Type
- Open Peer Commentary
- Information
- Copyright
- Copyright © The Author(s), 2023. Published by Cambridge University Press
References
Bruce, V., Green, P. R., & Georgeson, M. A. (2003). Visual perception: Physiology, psychology, & ecology. Psychology Press.Google Scholar
Chandran, K. S., & Ghosh, K. (2021). Recurrent convolutional neural networks trained by psychophysics data can predict EEG response to flicker. Perception, 50(ECVP2021 Supplement), 1–244. https://doi.org/10.1177/03010066211059887Google Scholar
Chandran, K. S., & Ghosh, K. (2022). An in-silica computation of alpha oscillations from apparently unrelated psychophysics data. https://doi.org/10.21203/rs.3.rs-1862596/v1CrossRefGoogle Scholar
Fan, R., Wang, L., Junaid Bocus, M., & Pitas, I. (2023). Computer stereo vision for autonomous driving: Theory and algorithms. Studies in Computational Intelligence, 41–70. https://doi.org/10.1007/978-3-031-18735-3_3CrossRefGoogle Scholar
Ghosh, K., & Chandran, K. S. (2021). A low-cost device and technique for generating big data in visual psychophysics to train brain models. Perception, 50(ECVP2021 Supplement), 1–244. https://doi.org/10.1177/03010066211059887Google Scholar
Gomez-Villa, A., Martín, A., Vazquez-Corral, J., Bertalmío, M., & Malo, J. (2020). Color illusions also deceive CNNs for low-level vision tasks: Analysis and implications. Vision Research, 176, 156–174. https://doi.org/10.1016/j.visres.2020.07.010CrossRefGoogle ScholarPubMed
Jahrens, M., & Martinetz, T. (2020). Solving Raven's progressive matrices with multi-layer relation networks. In 2020 International joint conference on neural networks (IJCNN). Jointly organized by the IEEE Computational Intelligence Society (CIS) and the International Neural Network Society (INNS), Glasgow, UK (pp. 1-6). https://doi.org/10.1109/ijcnn48605.2020.9207319CrossRefGoogle Scholar
Kriegeskorte, N., & Douglas, P. K. (2018). Cognitive computational neuroscience. Nature Neuroscience, 21(9), 1148–1160. https://doi.org/10.1038/s41593-018-0210-5CrossRefGoogle ScholarPubMed
Kubota, Y., Hiyama, A., & Inami, M. (2021). A machine learning model perceiving brightness optical illusions: Quantitative evaluation with psychophysical data. In Proceedings of the Augmented Humans International Conference 2021 (AHs '21). Association for Computing Machinery, New York, NY, USA (pp. 174–182). https://doi.org/10.1145/3458709.3458952CrossRefGoogle Scholar
Onishi, Y., Yoshida, T., Kurita, H., Fukao, T., Arihara, H., & Iwai, A. (2019). An automated fruit harvesting robot by using deep learning. ROBOMECH Journal, 6(1), 13. https://doi.org/10.1186/s40648-019-0141-2CrossRefGoogle Scholar
Read, J. C. A. (2015). The place of human psychophysics in modern neuroscience. Neuroscience, 296, 116–129. https://doi.org/10.1016/j.neuroscience.2014.05.036CrossRefGoogle ScholarPubMed
Turing, A. M. (1950). I. – Computing machinery and intelligence. Mind; A Quarterly Review of Psychology and Philosophy, LIX(236), 433–460. https://doi.org/10.1093/mind/lix.236.433CrossRefGoogle Scholar
Westlake, W. (2001). Is a one eyed racing driver safe to compete? Formula one (eye) or two? British Journal of Ophthalmology, 85(5), 619–624. https://doi.org/10.1136/bjo.85.5.619CrossRefGoogle ScholarPubMed
Zipser, D., & Andersen, R. A. (1988). A back-propagation programmed network that simulates response properties of a subset of posterior parietal neurons. Nature, 331(6158), 679–684. https://doi.org/10.1038/331679a0CrossRefGoogle 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