Collective intelligence for deep learning: A survey of recent developments
Open accessThe DOI matches its Crossref record; 70 of the 70 references it cites were found in a registry or an index.
Abstract
In the past decade, we have witnessed the rise of deep learning to dominate the field of artificial intelligence. Advances in artificial neural networks alongside corresponding advances in hardware accelerators with large memory capacity, together with the availability of large datasets enabled practitioners to train and deploy sophisticated neural network models that achieve state-of-the-art performance on tasks across several fields spanning computer vision, natural language processing, and reinforcement learning. However, as these neural networks become bigger, more complex, and more widely used, fundamental problems with current deep learning models become more apparent. State-of-the-art deep learning models are known to suffer from issues that range from poor robustness, inability to adapt to novel task settings, to requiring rigid and inflexible configuration assumptions. Collective behavior, commonly observed in nature, tends to produce systems that are robust, adaptable, and have less rigid assumptions about the environment configuration. Collective intelligence, as a field, studies the group intelligence that emerges from the interactions of many individuals. Within this field, ideas such as self-organization, emergent behavior, swarm optimization, and cellular automata were developed to model and explain complex systems. It is therefore natural to see these ideas incorporated into newer deep learning methods. In this review, we will provide a historical context of neural network research’s involvement with complex systems, and highlight several active areas in modern deep learning research that incorporate the principles of collective intelligence to advance its capabilities. We hope this review can serve as a bridge between the complex systems and deep learning communities.
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
“Numerous studies have proven that such systems do not give good enough results when it comes to more complex tasks, such as solving specific field problems in mathematics (in a broad sense, even at a low level), physics, chemistry, and various kinds of technical issues [5].”
From Contemporary approaches to integrating AI agents into library information processes (2025) · cites this paper as [5]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“In computer vision (CV), deep learning models are used in image recognition 27,57,75 and image generation 33,92 .”
MethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Human-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 · cited 3×
“Deep learning has also been incorporated into reinforcement learning (RL) to tackle vision-based computer games such as Doom (Ha and Schmidhuber, 2018) and Atari (Mnih et al. 2015), and play games with large search spaces such as Go (Silver et al.”
BackgroundLanguage Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372 · cited 1×
“In natural language processing (NLP), deep language models can generate text 7,58,59 and perform machine translation 76 .”
BackgroundMastering 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 · cited 1×
“Deep learning has also been incorporated into reinforcement learning (RL) to tackle vision-based computer games such as Doom 25 and Atari 46 , and play games with large search spaces such as Go 74 and Starcraft 90 .”
Advances in Neural Information Processing Systems 19
(2007) · The MIT Press eBooks · doi:10.52202/085713 · Cited by 15,539
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293 · cited 1×
“In computer vision (CV), deep learning models are used in image recognition 27,57,75 and image generation 33,92 .”
MethodAdvances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“Other types of neural network architectures, such as Graph Neural Networks 14,64,94 explicitly target self-organizing as a central feature, modeling the behavior of each node of a graph as identical neural network modules that pass messages to their neighbors defined by the edges of a graph.”
Research works printed but not linked: 31
- Baker B, Kanitscheider I, Markov T, et al. (2019) Emergent Tool Use from Multi-Agent Autocurricula. arXiv preprint arXiv:1909 . 07528.
- Bansal T, Pachocki J, Sidor S, et al. (2017) Emergent Complexity via Multi-Agent Competition. arXiv preprint arXiv:1710 . 03748.
- Bhatia J, 2021, Advances in Neural Information Processing Systems
- Brockman G, Cheung V, Pettersson L, et al. (2016) Openai Gym. arXiv preprint arXiv:1606 . 01540.
- Chollet F, 2015, Keras
- Conway J, 1970, Scientific American, 223, 4
- Ha D, 2020, Slime Volleyball Gym Environment
- Hill A, 2018, Stable Baselines
- Huang W, Mordatch I, Pathak D (2020) One policy to control them all: Shared modular policies for agent-agnostic control. In: International Conference on Machine Learning, pp. 4455–4464.
- Jenal M, 2011, What Ants Can Teach Us about the Market
- Kirsch L, Schmidhuber J (2020) Meta Learning Backpropagation and Improving it. arXiv preprint arXiv:2012 . 14905.
- Lévy P, 1997, Collective Intelligence
- Liu S, Lever G, Merel J, et al. (2019) Emergent Coordination through Competition. arXiv preprint arXiv:1902 .07151
- Ohsawa S, 2018, Neuron as an Agent
- Palm RB, Duque MG, Sudhakaran S, et al. (2022) Variational neural cellular automata. In: International Conference on Learning Representations.
- Peng Z, 2021, Advances in Neural Information Processing Systems, 34
- Radford A, 2018, Improving Language Understanding by Generative Pre-training
- Radford A, 2019, OpenAI blog, 1, 9
- Sanchez-Lengeling B, 2021, Distill, 6, e33
- Sandler M, Vladymyrov M, Zhmoginov A, et al. (2021) Meta-learning bidirectional update rules. In: International Conference on Machine Learning, pp. 9288–9300.
- Schmidhuber J, 2014, Who Invented Backpropagation?
- Schmidhuber J, 2020, Metalearning Machines Learn to Learn (1987)
- Schoenholz S, 2020, Advances in Neural Information Processing Systems, 33
- Seeley TD, 2010, Honeybee Democracy
- Suarez J, Du Y, Zhu C, et al. (2021) The neural mmo platform for massively multiagent research. In: Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track.
- Surowiecki J, 2005, The Wisdom of Crowds
- Tang Y, Ha D (2021) The sensory neuron as a transformer: Permutation-invariant neural networks for reinforcement learning. In: Thirty-Fifth Conference on Neural Information Processing Systems. https://attentionneuron.github.io
- Wang T, Liao R, Ba J, et al. (2018) Nervenet: Learning structured policy with graph neural networks. In: International Conference on Learning Representations.
- Wikipedia, 2022, Trajan’s Bridge at Alcantara
- Wolfram S, 2002, A New Kind of Science
- Zhang D, Choi C, Kim J, et al (2021) Learning to generate 3d shapes with generative cellular automata. In: International Conference on Learning Representations.
Cited by
How critical is brain criticality?
O’Byrne, J., & Jerbi, K. (2022) · Trends in Neurosciences · doi:10.1016/j.tins.2022.08.007 · Cited by 258
Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations
Marisca, I., Cini, A., & Alippi, C. (2022) · neural information processing systems · doi:10.52202/068431-2324 · Cited by 176
EvoJAX: hardware-accelerated neuroevolution
Tang, Y., Tian, Y., & Ha, D. (2022) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3520304.3528770 · Cited by 79
“Neural networks are a promising approach for modeling complex systems [9, 19], and neuroevolution has made great progress in developing methods for evolving neural networks to solve a wide range of problems.”
BackgroundSelf-citationLiang, B., van der Wal, C. N., Xie, K., Chen, Y., Brazier, F. M. T., Dulebenets, M. A., & Liu, Z. (2022) · Safety Science · doi:10.1016/j.ssci.2022.105955 · Cited by 49
A systematic review of robotic efficacy in coral reef monitoring techniques
Cardenas, J. A., Samadikhoshkho, Z., Rehman, A. U., Valle-Pérez, A. U., de León, E. H.-P., Hauser, C. A. E., Féron, É., & Ahmad, R. (2024) · Marine Pollution Bulletin · doi:10.1016/j.marpolbul.2024.116273 · Cited by 51
Metadata
- Authors
- Ha, D., & Tang, Y.
- Affiliations
- Google (United States) (US)
- Corresponding author
- Ha, David
- Tang, Yujin
- ORCID
- Venue
- Collective Intelligence
- Publisher
- SAGE Publications
- Published
- 2022-08
- Volume
- 1
- Issue
- 1
- ISSN
- 2633-9137 (ISSN-L)
- OpenAlex
- W4226229891
- Cited by
- 71
- References
- 67
- Citations by year
- 2026: 5 · 2025: 18 · 2024: 21 · 2023: 14 · 2022: 13
- FWCI
- 5.43
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Collective Intelligence (publishedVersion, cc-by-nc)
- arXiv (Cornell University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Complex Systems and Dynamics
- Keywords
- deep learning, complex systems, self-organization, emergent behavior, swarm intelligence optimization, cellular automata, robustness, adaptability, neural network architecture, artificial neural networks
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Collective intelligence for deep learning: A survey of recent developments. https://app.cochat.ai/papers/10.1177/26339137221114874
- The paper
- Ha, D., & Tang, Y. (2022). Collective intelligence for deep learning: A survey of recent developments. Collective Intelligence. https://doi.org/10.1177/26339137221114874
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.