How variability shapes learning and generalization
Open accessThe DOI matches its Crossref record; 34 of the 34 references it cites were found in a registry or an index.
Abstract
Learning is using past experiences to inform new behaviors and actions. Because all experiences are unique, learning always requires some generalization. An effective way of improving generalization is to expose learners to more variable (and thus often more representative) input. More variability tends to make initial learning more challenging, but eventually leads to more general and robust performance. This core principle has been repeatedly rediscovered and renamed in different domains (e.g., contextual diversity, desirable difficulties, variability of practice). Reviewing this basic result as it has been formulated in different domains allows us to identify key patterns, distinguish between different kinds of variability, discuss the roles of varying task-relevant versus irrelevant dimensions, and examine the effects of introducing variability at different points in training.
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
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
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203 · cited 1×
“Learning that is overly speci fi c to the training set yields progressively poorer performance on new items (so-called over fi tting, Figure IA), limiting the usefulness of the algorithm to correctly respond only to items that very closely resemble those that had been presented in training [140].”
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018) · Science · doi:10.1126/science.aar6404 · Cited by 3,562 · cited 1×
“In the past 10 years, the increase in processing power, optimization of learning algorithms, and, perhaps most importantly, increase in the size of training sets, has increasingly produced super-human performance on tasks ranging from object classification [169], to face recognition [170], to language processing [171]…”
BackgroundSpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Park, D. S., Chan, W., Zhang, Y., Chiu, C.-C., Zoph, B., Cubuk, E. D., & Le, Q. V. (2019) · Interspeech 2019 · doi:10.21437/interspeech.2019-2680 · Cited by 3,558
Context theory of classification learning
Medin, D. L., & Schaffer, M. M. (1978) · Psychological Review · doi:10.1037/0033-295x.85.3.207 · Cited by 3,061
The Effectiveness of Data Augmentation in Image Classification using Deep Learning
Perez, L., & Wang, J. (2017) · arXiv · doi:10.48550/arxiv.1712.04621 · Cited by 2,499
The echo chamber effect on social media
Cinelli, M., De Francisci Morales, G., Galeazzi, A., Quattrociocchi, W., & Starnini, M. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2023301118 · Cited by 2,092 · cited 1×
“Recent studies focusing on social networks formed by social media algorithms, which tend to pair users with like-minded users, show that doing so leads to echo chambers [187] with the power to further polarize people’s opinions [188].”
BackgroundLearning 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
Distributed practice in verbal recall tasks: A review and quantitative synthesis.
Cepeda, N. J., Pashler, H., Vul, E., Wixted, J. T., & Rohrer, D. (2006) · Psychological Bulletin · doi:10.1037/0033-2909.132.3.354 · Cited by 1,888 · cited 1×
“massed) learning of items consistently shows benefits’ [101] [101,131–135]”
Background
Cited by
Czyż, S. H., Wójcik, A. M., & Solarská, P. (2024) · Frontiers in Psychology · doi:10.3389/fpsyg.2024.1377122 · Cited by 10
“One could argue that the ultimate goal of practice is to transfer skills from one context to another, i.e., generalize practiced skill to a non-practice one (Raviv et al., 2022).”
BackgroundUnfamiliar face matching ability predicts the slope of face learning
Baker, K. A., & Mondloch, C. J. (2023) · Scientific Reports · doi:10.1038/s41598-023-32244-w · Cited by 6
Metadata
- Authors
- Raviv, L., Lupyan, G., & Green, S. C.
- Venue
- Trends in Cognitive Sciences
- Publisher
- Elsevier BV
- Published
- 2022-06
- Volume
- 26
- Issue
- 6
- Pages
- 462-483
- ISSN
- 1364-6613 (ISSN-L)
- OpenAlex
- W4280547462
- Cited by
- 206
- References
- 34
- FWCI
- 5.41
- Type
- journal article
- Language
- en
- Open access
- bronze
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.