A Developmental Approach to Machine Learning?
Open accessThe DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.
Abstract
Visual learning depends on both the algorithms and the training material. This essay considers the natural statistics of infant- and toddler-egocentric vision. These natural training sets for human visual object recognition are very different from the training data fed into machine vision systems. Rather than equal experiences with all kinds of things, toddlers experience extremely skewed distributions with many repeated occurrences of a very few things. And though highly variable when considered as a whole, individual views of things are experienced in a specific order - with slow, smooth visual changes moment-to-moment, and developmentally ordered transitions in scene content. We propose that the skewed, ordered, biased visual experiences of infants and toddlers are the training data that allow human learners to develop a way to recognize everything, both the pervasively present entities and the rarely encountered ones. The joint consideration of real-world statistics for learning by researchers of human and machine learning seems likely to bring advances in both disciplines.
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
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Basic objects in natural categories
Rosch, E., Mervis, C. B., Gray, W. D., Johnson, D. M., & Boyes-Braem, P. (1976) · Cognitive Psychology · doi:10.1016/0010-0285(76)90013-x · Cited by 5,643 · cited 1×
“…known as the “shape bias” in the developmental literature is an example of “one-shot” learning that has been observed in children’s natural category learning and has been replicated and extensively studied in the laboratory (e.g., Rosch et al., 1976; Landau et al., 1988; Samuelson and Smith, 2005).”
BackgroundBengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1×
“There are current approaches to machine learning (curriculum learning, and iterative teaching, for example) that seek to optimize learning through ordered and structured training sets (e.g., Bengio et al., 2009; Krueger and Dayan, 2009).”
BackgroundVariability in Early Communicative Development
Fenson, L., Dale, P. S., Reznick, J. S., Bates, E., Thal, D. J., Pethick, S. J., Tomasello, M., Mervis, C. B., & Stiles, J. (1994) · Monographs of the Society for Research in Child Development · doi:10.2307/1166093 · Cited by 2,790
Learning and development in neural networks: the importance of starting small
Elman, J. L. (1993) · Cognition · doi:10.1016/0010-0277(93)90058-4 · Cited by 1,988 · cited 1×
“But, the criticized idea is the developmentally right one (Elman, 1993).”
BackgroundExpertise for cars and birds recruits brain areas involved in face recognition
Gauthier, I., Skudlarski, P., Gore, J. C., & Anderson, A. W. (2000) · Nature Neuroscience · doi:10.1038/72140 · Cited by 1,418 · cited 1×
“Recognizing all these instances and categories requires visual training; people have to see dogs, cars and toasters to visually recognize instances of those categories (e.g., Gauthier et al., 2000; Malt and Majid, 2013; Kovack-Lesh et al., 2014).”
BackgroundHochstein (2002) · doi:10.1016/s0896-6273(02)01091-7 · Cited by 1,397
The importance of shape in early lexical learning
Landau, B., Smith, L. B., & Jones, S. S. (1988) · Cognitive Development · doi:10.1016/0885-2014(88)90014-7 · Cited by 1,174
Self-citationKriegeskorte, N. (2015) · Annual Review of Vision Science · doi:10.1146/annurev-vision-082114-035447 · Cited by 1,093
The Psychology and Neuroscience of Curiosity
Kidd, C., & Hayden, B. Y. (2015) · Neuron · doi:10.1016/j.neuron.2015.09.010 · Cited by 1,026
Cadieu, C. F., Hong, H., Yamins, D. L. K., Pinto, N., Ardila, D., Solomon, E. A., Majaj, N. J., & DiCarlo, J. J. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003963 · Cited by 824 · cited 2×
“There is growing excitement (Cadieu et al., 2014; Kriegeskorte, 2015; Marblestone et al., 2016) that we are at the tipping point for powerful new insights into both human and artificial intelligence and that these insights will emerge more rapidly by explicitly connecting advances in human…”
BackgroundLearning invariance from transformation sequences
Földiák, P. (1991) · Neural Computation · doi:10.1162/neco.1991.3.2.194 · Cited by 661 · cited 1×
“…extended time, the retinal information with respect to that object will necessarily and continuously change, revealing relevant transformations and the invariances for recognition that may be extendable to recognizing novel things (Földiák, 1991; Wiskott and Sejnowski, 2002; Li and DiCarlo, 2008).”
BackgroundLearning to recognize objects in egocentric activities
Fathi, A., Ren, X., & Rehg, J. M. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995444 · Cited by 557 · cited 1×
“Thus, they are biased to “what looks good” for the mature system, reflecting the outcomes of perceptual development and not necessarily the scenes that drove that development (e.g., Fathi et al., 2011; Foulsham et al., 2011; Smith et al., 2015).”
BackgroundCollisson, B. A., Grela, B., Spaulding, T., Rueckl, J. G., & Magnuson, J. S. (2015) · Developmental Science · doi:10.1111/desc.12219 · Cited by 65 · cited 2×
“We know that children who have difficulty in learning language – late-talkers, children with specific language impairment, children with autism – do not develop a robust shape bias (Jones, 2003; Jones and Smith, 2005; Tek et al., 2008; Collisson et al., 2015; Potrzeba et al., 2015).”
BackgroundYoung children’s self-generated object views and object recognition
James, K. H., Jones, S. S., Smith, L. B., & Swain, S. N. (2014) · Journal of Cognition and Development · doi:10.1080/15248372.2012.749481 · Cited by 51
Self-citation
Cited by
Unsupervised neural network models of the ventral visual stream
Zhuang, C., Yan, S., Nayebi, A., Schrimpf, M., Frank, M. C., DiCarlo, J. J., & Yamins, D. L. K. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2014196118 · Cited by 337
Intuitive physics learning in a deep-learning model inspired by developmental psychology
Piloto, L. S., Weinstein, A., Battaglia, P., & Botvinick, M. (2022) · Nature Human Behaviour · doi:10.1038/s41562-022-01394-8 · Cited by 118
Lessons from infant learning for unsupervised machine learning
Zaadnoordijk, L., Besold, T. R., & Cusack, R. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00488-2 · Cited by 65
Development of visual object recognition
Ayzenberg, V., & Behrmann, M. (2023) · Nature Reviews Psychology · doi:10.1038/s44159-023-00266-w · Cited by 41
Metadata
- Authors
- Smith, L. B., & Slone, L. K.
- Venue
- Frontiers in Psychology
- Publisher
- Frontiers Media SA
- Published
- 2017-12-05
- Volume
- 8
- Pages
- 2124-2124
- ISSN
- 1664-1078 (ISSN-L)
- OpenAlex
- W2771424446
- Cited by
- 107
- References
- 15
- FWCI
- 3.44
- Type
- journal article
- Language
- en
- Open access
- gold
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
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.