The DOI matches its Crossref record; 62 of the 62 references it cites were found in a registry or an index.
Human-level concept learning through probabilistic program induction
Abstract
Handwritten characters drawn by a model: Not only do children learn effortlessly, they do so quickly and with a remarkable ability to use what they have learned as the raw material for creating new stuff. Lake et al. describe a computational model that learns in a similar fashion and does so better than current deep learning algorithms. The model classifies, parses, and recreates handwritten characters, and can generate new letters of the alphabet that look “right” as judged by Turing-like tests of the model's output in comparison to what real humans produce. Science , this issue p. 1332
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Object detection algorithms are unable, in general, to recognize object categories outside of their training dataset, although ideally there should be the ability to recognize novel object categories (Lake et al. 2015;Hariharan and Girshick 2017).”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Lake et al. 2015
In the citing paper
“In contrast, humans (even children) can learn a visual concept quickly from very few given examples and can often generalize well (Biederman 1987b;Lake et al. 2015;FeiFei et al. 2006).”
From Deep Learning for Generic Object Detection: A Survey (2020) · cites this paper as Lake et al. 2015
In the citing paper
“Finally, higher-level systems in the brain may be able to implement Bayesian learning of sequential programs, which is a powerful means of one-shot learning (Lake et al., 2015).”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Lake et al., 2015
In the citing paper
“In particular, sequential programs were found to enable one-shot learning of new geometric/visual concepts (Lake et al., 2015).”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Lake et al., 2015
In the citing paper
“Structured, serial, hierarchical probabilistic programs have recently been shown to model aspects of human conceptual representation and compositional learning (Lake et al., 2015).”
From Toward an integration of deep learning and neuroscience (2016) · cites this paper as Lake et al., 2015
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
(2014) · Cited by 33,419
Self-citationHuman-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357
Backpropagation Applied to Handwritten Zip Code Recognition
LeCun, Y., Boser, B., Denker, J. S., Henderson, D., Howard, R. E., Hubbard, W., & Jackel, L. D. (1989) · Neural Computation · doi:10.1162/neco.1989.1.4.541 · Cited by 11,891
Caffe: Convolutional Architecture for Fast Feature Embedding
Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., & Darrell, T. (2014) · Proceedings of the 22nd ACM international conference on Multimedia · doi:10.1145/2647868.2654889 · Cited by 11,077
Hinton, G., Deng, L., Yu, D., Dahl, G., Mohamed, A.-R., Jaitly, N., Senior, A., Vanhoucke, V., Nguyen, P., Sainath, T., et al. (2012) · IEEE Signal Processing Magazine · doi:10.1109/msp.2012.2205597 · Cited by 10,260
Object Detection with Discriminatively Trained Part-Based Models
Felzenszwalb, P. F., Girshick, R. B., McAllester, D., & Ramanan, D. (2010) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2009.167 · Cited by 9,853
An overview of statistical learning theory
Vapnik, V. N. (1999) · IEEE Transactions on Neural Networks · doi:10.1109/72.788640 · Cited by 6,420
Recognition-by-components: A theory of human image understanding.
Biederman, I. (1987) · Psychological Review · doi:10.1037/0033-295x.94.2.115 · Cited by 5,621
Flagged first, then by citations
Research works printed but not linked: 21
- E. M. Markman Categorization and Naming in Children (MIT Press Cambridge MA 1989).
- Krizhevsky A., Sutskever I., Hinton G. E., Adv. Neural Inf. Process. Syst. 25, 1097–1105 (2012).
- N. D. Goodman J. B. Tenenbaum T. Gerstenberg Concepts: New Directions E. Margolis S. Laurence Eds. (MIT Press Cambridge MA 2015).
- R. Salakhutdinov J. Tenenbaum A. Torralba in JMLR Workshop and Conference Proceedings vol. 27 Unsupervised and Transfer Learning Workshop I. Guyon G. Dror V. Lemaire G. Taylor D. Silver Eds. (Microtome Brookline MA 2012) pp. 195–206.
- Mansinghka V. K., Kulkarni T. D., Perov Y. N., Tenenbaum J. B., Adv. Neural Inf. Process. Syst. 26, 1520–1528 (2013).
- M.-P. Dubuisson A. K. Jain in Proceedings of the 12th IAPR International Conference on Pattern Recognition Vol. 1 Conference A: Computer Vision and Image Processing Jerusalem Israel 9 to 13 October 1994 (IEEE New York 1994) pp. 566–568.
- G. Koch R. S. Zemel R. Salakhutdinov paper presented at ICML Deep Learning Workshop Lille France 10 and 11 July 2015.
- Hinton G. E., Nair V., Adv. Neural Inf. Process. Syst. 19, 515–522 (2006).
- P. Liang M. I. Jordan D. Klein in Proceedings of the 27th International Conference on Machine Learning Haifa Israel 21 to 25 June 2010 (International Machine Learning Society Princeton NJ 2010) pp. 639–646.
- I. Hwang A. Stuhlm¨ller N. D. Goodman (2011) http://arxiv.org/abs/1110.5667. · arXiv
- E. Dechter J. Malmaud R. P. Adams J. B. Tenenbaum in Proceedings of the 23rd International Joint Conference on Artificial Intelligence F. Rossi Ed. Beijing China 3 to 9 August 2013 (AAAI Press/International Joint Conferences on Artificial Intelligence Menlo Park CA 2013) pp. 1302–1309.
- J. Rule E. Dechter J. B. Tenenbaum in Proceedings of the 37th Annual Conference of the Cognitive Science Society D. C. Noelle et al . Eds. Pasadena CA 22 to 25 July 2015 (Cognitive Science Society Austin TX 2015) pp. 2051–2056.
- T. D. Ullman A. Stuhlmuller N. Goodman J. B. Tenenbaum in Proceedings of the 36th Annual Conference of the Cognitive Science Society Quebec City Canada 23 to 26 July 2014 (Cognitive Science Society Austin TX 2014) pp. 1640–1645.
- B. M. Lake C.-y. Lee J. R. Glass J. B. Tenenbaum in Proceedings of the 36th Annual Conference of the Cognitive Science Society Quebec City Canada 23 to 26 July 2014 (Cognitive Science Society Austin TX 2014) pp. 803–808.
- A. Graves (2014) http://arxiv.org/abs/1308.0850. · arXiv
- K. Gregor I. Danihelka A. Graves D. J. Rezende D. Wierstra in Proceedings of the International Conference on Machine Learning (ICML) Lille France 6 to 11 July 2015 (International Machine Learning Society Princeton NJ 2015) pp. 1462–1471.
- Chung J., et al.., Adv. Neural Inf. Process. Syst. 28, (2015).
- B. M. Lake R. Salakhutdinov J. B. Tenenbaum paper presented at the 34th Annual Conference of the Cognitive Science Society Sapporo Japan 1 to 4 August 2012.
- B. M. Lake R. Salakhutdinov J. B. Tenenbaum paper presented at the Advances in Neural Information Processing Systems 26 City Country Dates Month Year.
- B. M. Lake thesis MIT Cambridge MA (2014).
- T. J. O’Donnell thesis Harvard University Cambridge MA (2011).
Cited by
Sorted by citations
Items 601–700 of 1,006
Generative Temporal Models with MemoryPreprint
Gemici, M., Hung, C.-C., Santoro, A., Wayne, G., Mohamed, S., Rezende, D. J., Amos, D., & Lillicrap, T. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.04649 · Cited by 78
Learning Hierarchical Priors in VAEsPreprint
Klushyn, A., Chen, N., Kurle, R., Cseke, B., & van der Smagt, P. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1905.04982 · Cited by 42
Machine learning in Alzheimer’s disease drug discovery and target identification
Geng, C., Wang, Z., & Tang, Y. (2024) · Ageing Research Reviews · doi:10.1016/j.arr.2023.102172 · Cited by 34
Training a Probabilistic Graphical Model With Resistive Switching Electronic Synapses
Eryilmaz, S. B., Neftci, E., Joshi, S., Kim, S., BrightSky, M., Lung, H.-L., Lam, C., Cauwenberghs, G., & Wong, H.-S. P. (2016) · IEEE Transactions on Electron Devices · doi:10.1109/ted.2016.2616483 · Cited by 34
Neural circuits and symbolic processing
Do, Q. H., & Hasselmo, M. E. (2021) · Neurobiology of Learning and Memory · doi:10.1016/j.nlm.2021.107552 · Cited by 38
“Applying this hierarchical framework to Bayesian problem learning, researchers have simulated inventing a new handwritten letter from basic strokes, or designing a new mode of transportation from simple building blocks (Lake et al., 2015).”
InfluentialCD-FSOD: A Benchmark For Cross-Domain Few-Shot Object Detection
Xiong, W. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096216 · Cited by 34
“In these cases, even humans have trouble recognizing new categories that vary too greatly between examples or differ from prior experience [3, 4].”
BackgroundAttention heads of large language models
Zheng, Z., Wang, Y., Huang, Y., Song, S., Yang, M., Tang, B., Xiong, F., & Li, Z. (2025) · Patterns · doi:10.1016/j.patter.2025.101176 · Cited by 143
Learning to Recognize Actions From Limited Training Examples Using a Recurrent Spiking Neural Model
Panda, P., & Srinivasa, N. (2018) · Frontiers in Neuroscience · doi:10.3389/fnins.2018.00126 · Cited by 33
NECST: Neural Joint Source-Channel Coding.
Choi, K., Tatwawadi, K., Weissman, T., & Ermon, S. (2018) · Cited by 32
A Human-Like Semantic Cognition Network for Aspect-Level Sentiment Classification
Lei, Z., Yang, Y., Yang, M., Zhao, W. D., Guo, J. F., & Liu, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016650 · Cited by 36
Towards Structured Evaluation of Deep Neural Network Supervisors
Henriksson, J., Berger, C., Borg, M., Tornberg, L., Englund, C., Sathyamoorthy, S. R., & Ursing, S. (2019) · IEEE International Conference on Artificial Intelligence Testing (AITest) · doi:10.1109/aitest.2019.00-12 · Cited by 34
Neural algorithms and computing beyond Moore's law
Aimone, J. B. (2019) · Communications of the ACM · doi:10.1145/3231589 · Cited by 35
Online Continual Learning on Sequences
Parisi, G. I., & Lomonaco, V. (2020) · Studies in computational intelligence · doi:10.1007/978-3-030-43883-8_8 · Cited by 39
Chen, L., Tian, X., Chai, G., Zhang, X., & Chen, E. (2021) · Remote Sensing · doi:10.3390/rs13071269 · Cited by 35
Temporal and state abstractions for efficient learning, transfer, and composition in humans.
Xia, L., & Collins, A. G. E. (2021) · Psychological Review · doi:10.1037/rev0000295 · Cited by 33
Predicate learning in neural systems: using oscillations to discover latent structure
Martin, A. E., & Doumas, L. A. A. (2019) · Current Opinion in Behavioral Sciences · doi:10.1016/j.cobeha.2019.04.008 · Cited by 34
Helpless infants are learning a foundation model
Cusack, R., Ranzato, M., & Charvet, C. J. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.05.001 · Cited by 37
“Foundation models bridge a longstanding gap between humans, who can learn a new task with just a few examples, and machines, which until now had needed thousands of labelled examples [61].”
BackgroundPragmatic Inference and Visual Abstraction Enable Contextual Flexibility During Visual Communication
Fan, J. E., Hawkins, R. D., Wu, M., & Goodman, N. D. (2019) · Computational Brain & Behavior · doi:10.1007/s42113-019-00058-7 · Cited by 35
NetTailor: Tuning the Architecture, Not Just the Weights
Morgado, P. M., & Vasconcelos, N. M. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00316 · Cited by 34
3D Highway Curve Reconstruction From Mobile Laser Scanning Point Clouds
Zhang, Z., Li, J., Guo, Y., Yang, C., & Wang, C. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2946259 · Cited by 33
“We adopt the probabilistic program induction strategy [19] to perform curve reconstruction, as the strategy can automatically recognize the types of curves and estimate the values of the curve variables at the same time.”
MethodBudget-Aware Adapters for Multi-Domain Learning
Berriel, R. F., Lathuilière, S., Nabi, M., Klein, T., Oliveira-Santos, T., Sebe, N., & Ricci, E. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00047 · Cited by 33
Deep imitator: Handwriting calligraphy imitation via deep attention networks
Zhao, B., Tao, J., Yang, M., Tian, Z., Fan, C., & Bai, Y. (2020) · Pattern Recognition · doi:10.1016/j.patcog.2019.107080 · Cited by 33
A Comparison of Few-Shot Learning Methods for Underwater Optical and Sonar Image Classification
Ochal, M., Vazquez, J., Pétillot, Y., & Wang, S. (2020) · Global Oceans 2020: Singapore – U.S. Gulf Coast · doi:10.1109/ieeeconf38699.2020.9389475 · Cited by 35
“measures assume a different but similar dataset used during both the evaluation and training of FSL models. As such models are typically trained and evaluated with a single dataset, such as Omniglot [19] for grayscale images and Mini-ImageNet [16] for colored images. However, Omniglot, a hand-written character dataset…”
MethodSkeleton-Based Dynamic Hand Gesture Recognition Using an Enhanced Network with One-Shot Learning
Ma, C., Zhang, S., Wang, A., Qi, Y., & Chen, G. (2020) · Applied Sciences · doi:10.3390/app10113680 · Cited by 33
“For the statistics-based, Lake [37] adopted the Bayesian framework realized one-shot learning of handwritten character pictures based on the statistical point of view and the way humans learn things, triggering the new wave of one-shot learning.”
MethodMetacognitive resources for adaptive learning⋆
Cortese, A. (2021) · Neuroscience Research · doi:10.1016/j.neures.2021.09.003 · Cited by 39
“Machines can reach and periodically surpass human performance in specific contexts [e.g., Atari games, or chess (Lake et al., 2015; Sorokin et al., 2015)].”
Das, P., & Varshney, L. R. (2022) · IEEE Signal Processing Magazine · doi:10.1109/msp.2022.3141365 · Cited by 38
“Nevertheless, a number of works aim for novel, creative generation using deep generative models like VAEs or GANs, formulating the task as a few-/one-shot generation problem [30]–[32] or as a style-ambiguous design [33].”
BackgroundBennetot, A., Franchi, G., Ser, J. D., Chatila, R., & Díaz-Rodríguez, N. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109947 · Cited by 33
“For example, handwritten symbols can be learned from only a few examples using a compositional representation of strokes [30].”
BackgroundAn information-theoretic analysis of deep latent-variable modelsPreprint
Alemi, A. A., Poole, B., Fischer, I., Dillon, J. V., Saurous, R. A., & Murphy, K. P. (2018) · arXiv (Cornell University) · Cited by 35
Safer Classification by SynthesisPreprint
Wang, W. Y., Wang, A., Tamar, A., Chen, X., & Abbeel, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.08534 · Cited by 39
Detecting Out-of-Distribution Inputs in Deep Neural Networks Using an Early-Layer OutputPreprint
Abdelzad, V., Czarnecki, K., Salay, R., Denounden, T., Vernekar, S., & Phan, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.10307 · Cited by 48
A Comprehensive Overview and Survey of Recent Advances in Meta-LearningPreprint
Peng, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.11149 · Cited by 58
Mapping Citizen Science through the Lens of Human-Centered AI
Rafner, J. F., Gajdacz, M., Kragh, G., Hjorth, A., Gander, A. J., Palfi, B., Berditchevskiaia, A., Grey, F., Gal, K., Segal, A., et al. (2022) · Human Computation · doi:10.15346/hc.v9i1.133 · Cited by 38
Building More Explainable Artificial Intelligence With Argumentation
Zeng, Z., Miao, C., Leung, C., & Chin, J. J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11353 · Cited by 32
Dif-MAML: Decentralized Multi-Agent Meta-Learning
Kayaalp, M., Vlaski, S., & Sayed, A. H. (2022) · IEEE Open Journal of Signal Processing · doi:10.1109/ojsp.2021.3140000 · Cited by 35
“The Omniglot dataset comprises 1623 characters from 50 different alphabets.”
InfluentialDeep spatial representation learning of polyamide nanofiltration membranes
Zhang, Z., Luo, Y., Peng, H., Chen, Y., Liao, R., & Zhao, Q. (2020) · Journal of Membrane Science · doi:10.1016/j.memsci.2020.118910 · Cited by 32
On the Importance of Distractors for Few-Shot Classification
Das, R., Wang, Y.-X., & Moura, J. M. F. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00890 · Cited by 32
“To overcome this limitation, few-shot classification has been proposed as a generic framework for learning to classify with very limited supervision [12, 31, 34, 59].”
Open Long-Tailed Recognition in a Dynamic World
Liu, Z., Miao, Z., Zhan, X., Wang, J., Gong, B., & Yu, S. X. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3200091 · Cited by 38
“Although natural data distributions contain head, tail, and open classes, existing classification approaches focus mostly on either the head [2], [3] or the tail [4], [5], and often in a closed setting [6], [7] (Fig.”
BackgroundNeurosymbolic Models for Computer Graphics
Ritchie, D., Guerrero, P., Jones, R. K., Mitra, N. J., Schulz, A., Willis, K. D. D., & Wu, J. (2023) · Computer Graphics Forum · doi:10.1111/cgf.14775 · Cited by 43
Huang, H. (2017) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/aa6ddc · Cited by 35
Going Beyond the Point Neuron: Active Dendrites and Sparse Representations for Continual LearningPreprint
Grewal, K., Forest, J., Cohen, B. P., & Ahmad, S. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.10.25.465651 · Cited by 35
“While Supermasks can learn hundreds of Omniglot (Lake et al., 2015) classes in sequence, computing the appropriate subnetwork is largely decoupled from the inference procedure and must be done on the side, a limitation of this approach.”
BackgroundLalor, J. P., Wu, H., & Yu, H. Q. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1434 · Cited by 37
Baskaran, A., Kautz, E. J., Chowdhary, A., Ma, W., Yener, B., & Lewis, D. (2021) · JOM · doi:10.1007/s11837-021-04805-9 · Cited by 39
Few-Shot and Continual Learning with Attentive Independent Mechanisms
Lee, E., Huang, C., & Lee, C. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00932 · Cited by 32
“Omniglot [27] has over 1,623 characters from 50 diferent alphabets, where each character has 20 handwritten images of size 28 × 28.”
BackgroundLi, J., & Li, B. (2021) · Communications in Theoretical Physics · doi:10.1088/1572-9494/ac2055 · Cited by 32
Controllable SiOx Nanorod Memristive Neuron for Probabilistic Bayesian Inference
Choi, S., Kim, G. S., Yang, J., Cho, H., Kang, C., & Wang, G. (2021) · Advanced Materials · doi:10.1002/adma.202104598 · Cited by 32
When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework
Zou, X., Yan, Y., Xue, J., Chen, S., & Wang, H. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i5.20474 · Cited by 30
Ayzenberg, V., & Lourenco, S. F. (2022) · eLife · doi:10.7554/elife.74943 · Cited by 31
“handwritten characters) suggests that a skeletonlike compositional structure is central to one- shot categorization (Lake et al., 2011; Lake et al., 2015).”
BackgroundDiagnosing Ensemble Few-Shot Classifiers
Yang, W., Ye, X., Zhang, X., Xiao, L., Xia, J., Wang, Z., Zhu, J. J., Pfister, H., & Liu, S. (2022) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2022.3182488 · Cited by 34
“The remaining 8 base learners are pre-trained on external datasets, e.g., natural images in ImageNet [54], handwritten characters in Omniglot [55].”
BackgroundResultRevisiting Unsupervised Meta-Learning via the Characteristics of Few-Shot Tasks
Ye, H.-J., Han, L., & Zhan, D. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3179368 · Cited by 31
“THE Few-Shot Learning (FSL) ability [1], [2], i.”
Probabilistic Compositional Embeddings for Multimodal Image Retrieval
Neculai, A., Chen, Y., & Akata, Z. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00501 · Cited by 33
“Compositional learning provides an important functionality in an artificial intelligent machine [30, 31].”
BackgroundOptimized Generic Feature Learning for Few-shot Classification across DomainsPreprint
Saikia, T., Brox, T., & Schmid, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.07926 · Cited by 31
“…consists of 10 datasets from diverse domains: ILSVRC-2012 [45] (the ImageNet dataset, consisting of natural images with 1000 categories), Omniglot [28] (hand-written characters, 1623 classes), Air-craft [34] (dataset of aircraft images, 100 classes) , CUB-200-2011 [58] (dataset of Birds, 200…”
Killer Robots as cultural techniques
Karppi, T., Böhlen, M., & Granata, Y. (2016) · International Journal of Cultural Studies · doi:10.1177/1367877916671425 · Cited by 30
Principal characteristic networks for few-shot learning
Zheng, Y. L., Wang, R., Yang, J., Xue, L., & Hu, M. Q. (2019) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2019.02.006 · Cited by 32
Heterogeneous Model Reuse via Optimizing Multiparty Multiclass Margin
Wu, X.-Z., Liu, S., & Zhou, Z. (2019) · Bristol Research (University of Bristol) · Cited by 30
de Lima, R. P., Welch, K. F., Barrick, J. E., Marfurt, K. J., Burkhalter, R., Cassel, M., & Soreghan, G. S. (2020) · Palaios · doi:10.2110/palo.2019.102 · Cited by 31
“Although researchers are working with CNN models to perform image recognition using only a few examples for training, in some cases a single example per class (e.g., Koch 2015; Lake et al. 2015; Santoro et al. 2016), most CNN applications use hundreds to hundreds of thousands of examples per class.”
MethodHa, T., Sah, Y. J., Park, Y., & Lee, S. (2020) · Behaviour and Information Technology · doi:10.1080/0144929x.2020.1846789 · Cited by 33
“Studies have examined attention mechanisms (Vaswani et al. 2017), stochastic and-or-graphs (Si and Zhu 2013), and concept learning through probabilistic programme induction (Lake, Salakhutdinov, and Tenenbaum 2015).”
BackgroundOne-shot learning for acoustic diagnosis of industrial machines
Ntalampiras, S. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.114984 · Cited by 31
Li, X., Zhu, R., Ye, H., Jiang, C., & Benslimane, A. (2021) · Safety Science · doi:10.1016/j.ssci.2021.105315 · Cited by 31
Cloud2Curve: Generation and Vectorization of Parametric Sketches
Das, A., Yang, Y., Hospedales, T. M., Xiang, T., & Song, Y.-Z. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00701 · Cited by 34
A Flash-Based Multi-Bit Content-Addressable Memory with Euclidean Squared Distance
Kazemi, A., Sahay, S., Saxena, A., Sharifi, M. M., Niemier, M. T., & Hu, X. S. (2021) · International Symposium on Low Power Electronics and Design (ISLPED) · doi:10.1109/islped52811.2021.9502488 · Cited by 30
“The FeFET based MCAM could achieve higher accuracies than TCAM-based approaches for few-shot learning with MANNs for a small dataset (Om-niglot [9]), but the achievable accuracies are still lower than software baselines.”
MethodGuo, N., Di, K., Liu, H., Wang, Y., & Qiao, J. (2021) · Displays · doi:10.1016/j.displa.2021.102065 · Cited by 30
Task2Sim: Towards Effective Pre-training and Transfer from Synthetic Data
Mishra, S., Panda, R., Phoo, C. P., Chen, C.-F. R., Karlinsky, L., Saenko, K., Saligrama, V., & Feris, R. (2022) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52688.2022.00898 · Cited by 31
“• Symbolic Images: SVHN(S) [38], Omniglot(S) [28], USPS(U) [20]”
A General Descent Aggregation Framework for Gradient-Based Bi-Level Optimization
Liu, R., Mu, P., Yuan, X., Zeng, S., & Zhang, J. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3140249 · Cited by 36
Cross-Domain Few-Shot Graph Classification
Hassani, K. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i6.20642 · Cited by 30
Zhou, Z., Wang, L., & Yan, Z. (2022) · Physics Letters A · doi:10.1016/j.physleta.2022.128373 · Cited by 30
“With the quick development of cloud computing resources and mass data, deep learning [24,25] has been used in many fields containing cognitive science [26], image recognition [27], genomics [28], industrial areas [29,30], and etc.”
BackgroundZhao, J., Qian, X., Zhang, Y., Shan, D., Liu, X., Coleman, S., & Kerr, D. (2023) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02080-w · Cited by 30
“Few-shot learning (Fei-Fei et al., 2006; Lake et al., 2011, 2015)isanewresearchtopicinrecentyears.”
Survey on leveraging pre-trained generative adversarial networks for image editing and restoration
Liu, M., Wei, Y., Wu, X., Zuo, W., & Zhang, L. (2023) · Science China Information Sciences · doi:10.1007/s11432-022-3679-0 · Cited by 38
“…(Flowers [150]), IN (ImageNet [59]), LF (LFW [151]), LHQ (Landscapes HQ [152]), LS (LSUN [37]), MF (MetFaces [16]), MN (MNIST [61]), OM (Omniglot [153]), P3 (Places365 [67]), PL (Places [154]), PT (Oxford-IIIT Pet [155], aka Cats and Dogs), RA (RAVDESS [156]), SC (Stanford Cars [157]), SS…”
Universal Representations: A Unified Look at Multiple Task and Domain Learning
Li, W., Liu, X., & Bilen, H. (2023) · International Journal of Computer Vision · doi:10.1007/s11263-023-01931-6 · Cited by 41
“The MetaDataset (Triantafillou et al., 2020) is a few-shot classification benchmark that initially consisted of ten datasets: ILSVRC_2012 (ImageNet) (Russakovsky et al., 2015), Omniglot (Lake et al., 2015), FGVC-Aircraft (Aircraft) (Maji et al., 2013), CUB-200-2011 (Birds) (Wah et al., 2011), Describable Textures (DTD)…”
InfluentialBonawitz, E. B., Ullman, T. D., Bridgers, S., Alison Gopnik, C., & Tenenbaum, J. B. (2019) · Cognitive Science · doi:10.1111/cogs.12765 · Cited by 34
Self-citationTask-Robust Model-Agnostic Meta-LearningPreprint
Collins, L., Mokhtari, A., & Shakkottai, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.04766 · Cited by 30
Müller, H., & Holzinger, A. (2021) · Artificial Intelligence · doi:10.1016/j.artint.2021.103546 · Cited by 30
Out-of-distribution Detection via Frequency-regularized Generative Models
Cai, M., & Li, Y. (2023) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv56688.2023.00548 · Cited by 29
“The OOD datasets includes SVHN [33], LSUN [54], MNIST [9], KMNIST [25], Omniglot [23], NotMNIST , Noise , and Constant .”
MethodScattering Attribute Embedded Network for Few-Shot SAR ATR
Qin, J., Zou, B., Chen, Y., Li, H., & Zhang, L. (2024) · IEEE Transactions on Aerospace and Electronic Systems · doi:10.1109/taes.2024.3373379 · Cited by 29
“For humans, when learning new patterns, they often incorporate the typical structural attributes of the current target to assist in the recognition process [22], [34].”
BackgroundA Novel Recurrent Neural Network for Improving Redundant Manipulator Motion Planning Completeness
Li, Y., Li, S., & Hannaford, B. (2018) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2018.8461204 · Cited by 29
What does the mind learn? A comparison of human and machine learning representations
Spicer, J., & Sanborn, A. N. (2019) · Current Opinion in Neurobiology · doi:10.1016/j.conb.2019.02.004 · Cited by 29
Ghost Imputation: Accurately Reconstructing Missing Data of the Off Period
Rawassizadeh, R., Keshavarz, H., & Pazzani, M. J. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2914653 · Cited by 29
“learn from a single labeled instance [15], [23], our algorithm tries to estimate the missing data from the first similar instance that can be found in a sequential search of the dataset.”
BackgroundFaster Attend-Infer-Repeat with Tractable Probabilistic Models.
Stelzner, K., Peharz, R., & Kristian Kersting, B. (2019) · TU/e Research Portal · Cited by 29
Towards Interpretable Object Detection by Unfolding Latent Structures
Wu, T., & Song, X. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00613 · Cited by 30
Relating Visual Production and Recognition of Objects in Human Visual Cortex
Fan, J. E., Wammes, J. D., Gunn, J. B., Yamins, D. L. K., Norman, K. A., & Turk‐Browne, N. B. (2019) · Journal of Neuroscience · doi:10.1523/jneurosci.1843-19.2019 · Cited by 29
Li, Y., & Mei, F. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-09142-8 · Cited by 30
Lu, Y., Peng, X., Yang, D., Yang, M., & Zhong, W. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3058426 · Cited by 29
Few-shot image classification algorithm based on attention mechanism and weight fusion
Meng, X., Wang, X., Yin, S., & Li, H. (2023) · Journal of Engineering and Applied Science · doi:10.1186/s44147-023-00186-9 · Cited by 31
“Dataset This experiment uses two reference datasets in few-shot learning: the omniglot dataset [41] and the miniImageNet dataset [28].”
MethodParameter Transfer Unit for Deep Neural Networks
Zhang, Y., Zhang, Y., & Yang, Q. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-16145-3_7 · Cited by 30
Deep learning for face image synthesis and semantic manipulations: a review and future perspectives
Abdolahnejad, M., & Liu, P. X. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09835-4 · Cited by 32
Question Asking as Program GenerationPreprint
Rothe, A., Lake, B. M., & Gureckis, T. M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1711.06351 · Cited by 34
Self-citationNeural Relational Inference with Fast Modular Meta-learningPreprint
Alet, F., Weng, E., Lozano-Perez, T., & Kaelbling, L. (2023) · Neural Information Processing Systems · doi:10.48550/arxiv.2310.07015 · Cited by 64
“The literature in meta-learning (Schmidhuber, 1987; Thrun & Pratt, 2012; Lake et al., 2015) and multi-task learning (Torrey & Shavlik, 2010) is very extensive.”
BackgroundAligning machine and human visual representations across abstraction levels
Muttenthaler, L., Greff, K., Born, F., Spitzer, B., Kornblith, S., Mozer, M. C., Müller, K. R., Unterthiner, T., & Lampinen, A. K. (2025) · Nature · doi:10.1038/s41586-025-09631-6 · Cited by 60
Semi-Supervised Few-Shot Learning with Prototypical Networks.
Boney, R., & Ilin, A. (2017) · Cited by 28
KANDINSKY Patterns as IQ-Test for Machine Learning
Holzinger, A., Kickmeier-Rust, M., & Müller, H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29726-8_1 · Cited by 28
Learning transferable features in meta-learning for few-shot text classification
Xu, J., & Du, Q.-F. (2020) · Pattern Recognition Letters · doi:10.1016/j.patrec.2020.05.007 · Cited by 25
GenDet: Meta Learning to Generate Detectors From Few Shots
Liu, L., Wang, B., Kuang, Z., Xue, J., Chen, Y., Yang, W., Liao, Q., & Zhang, W. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3053005 · Cited by 30
“Others learn prior knowledge by parts and relations [36], [37], super classes [38] or latent variables.”
BackgroundOn the Practicality of Deterministic Epistemic Uncertainty
Postels, J., Segù, M., Sun, T., Sieber, L. D., Gool, L. V., Yu, F., & Tombari, F. (2021) · Repository for Publications and Research Data (ETH Zurich) · doi:10.3929/ethz-b-000593816 · Cited by 51
Zhang, B., Li, M.-Y., Li, W., Jiang, Z., Khan, U., Wang, L., & Fan-yun, W. A. N. G. (2021) · Journal of Central South University · doi:10.1007/s11771-021-4707-9 · Cited by 27
Few-shot learning for ear recognition
Zhang, J., Yu, W., Yang, X., & Deng, F. Y. (2019) · International Conference on Image, Video and Signal Processing (IVSP) · doi:10.1145/3317640.3317646 · Cited by 28
Torchmeta: A Meta-Learning library for PyTorchPreprint
Deleu, T., Würfl, T., Samiei, M., Cohen, J., & Bengio, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.06576 · Cited by 67
Meta Discovery: Learning to Discover Novel Classes given Very Limited DataPreprint
Chi, H., Liu, F., Han, B., Yang, W., Lan, L., Liu, T., Niu, G., Zhou, M., & Sugiyama, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.04002 · Cited by 31
“Results on OmniGlot.”
InfluentialNeuroplasticity enables bio-cultural feedback in Paleolithic stone-tool making
Hecht, E. E., Pargeter, J., Khreisheh, N., & Stout, D. (2023) · Scientific Reports · doi:10.1038/s41598-023-29994-y · Cited by 28
Unifying Principles of Generalization: Past, Present, and Future
Wu, C. M., Meder, B., & Schulz, E. (2024) · Annual Review of Psychology · doi:10.1146/annurev-psych-021524-110810 · Cited by 39
“…rule-based generalization (i.e., proposing explicit hypotheses) play an important role in modern theories of structure learning (Kemp & Tenenbaum 2008) and program induction (Lake et al. 2015, Rule et al. 2020), which use a probabilistic framework to add flexibility to the rigid structure of rules.”
Ingredients of intelligence: From classic debates to an engineering roadmap
Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017) · Behavioral and Brain Sciences · doi:10.1017/s0140525x17001224 · Cited by 26
Self-citationLearning Relational Representations with Auto-encoding Logic Programs
Dumancic, S., Guns, T., Meert, W., & Blockeel, H. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/842 · Cited by 27
Metadata
- Authors
- Lake, B. M., Salakhutdinov, R., & Tenenbaum, J. B.
- Affiliations
- New York University (US)
- University of Toronto (CA)
- Massachusetts Institute of Technology (US)
- Corresponding author
- Lake, Brenden M.
- Venue
- Science
- Published
- 2015-12-11
- Volume
- 350
- Issue
- 6266
- Pages
- 1332-1338
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W2194321275
- Cited by
- 2,817
- References
- 62
- Citations by year
- 2026: 137 · 2025: 186 · 2024: 256 · 2023: 281 · 2022: 300 · 2021: 415 · 2020: 400 · 2019: 393 · 2018: 223 · 2017: 145 · 2016: 79 · 2015: 1
- FWCI
- 146.15
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Science (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Office of Naval Research (W911NF-08-1-0242, W911NF-13-1-2012, N000141310333)
- Army Research Office
- Canadian Institute for Advanced Research
- Natural Sciences and Engineering Research Council of Canada
- NSF Science and Technology Center (CCF-1231216)
- Moore-Sloan Data Science Environment at NYU
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Bayesian Modeling and Causal Inference
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Keywords
- concept learning, one-shot classification, handwritten character recognition, alphabet, visual concepts, visual Turing test
- MeSH terms
- Machine Learning, Algorithms, Bayes Theorem, Computer Simulation, Concept Formation, Generalization, Psychological, Humans
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
