paper
referenced-only
2021
paper:doi-10-1016-j-cobeha-2021-01-002Meta-learning in natural and artificial intelligence
ByWang JX
Original abstract (expand)
Meta-learning, or learning to learn, has gained renewed interest in recent years within the artificial intelligence community. However, meta-learning is incredibly prevalent within nature, has deep roots in cognitive science and psychology, and is currently studied in various forms within neuroscience. The aim of this review is to recast previous lines of research in the study of biological intelligence within the lens of meta-learning, placing these works into a common framework. More recent points of interaction between AI and neuroscience will be discussed, as well as interesting new directions that arise under this perspective.
Related work— refs + corpus + external arXiv
Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.
- ≈ 81%
- ≈ 78%
- ≈ 76%
- MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of MindRashed Shelim, Walid Saad, Naren Ramakrishna Lingyi Wang2026≈ 76%
- What Neuroscience Can Teach AI About Learning in Continuously Changing EnvironmentsBruno Averbeck, Georgia Koppe Daniel Durstewitz2025≈ 76%
- Meta-Representational Predictive Coding: Biomimetic Self-Supervised LearningKarl Friston, Rajesh P. N. Rao Alexander Ororbia2025≈ 75%
- ≈ 75%
- Metarobotics for Industry and Society: Vision, Technologies, and OpportunitiesEric Guiffo Kaigom2024≈ 75%
- ≈ 75%
- Artificial Intelligence for Collective Intelligence: A National-Scale Research StrategyNirav Ajmeri (1), Mike Batty (2), Michaela Black (3), John Cartlidge (1), Robert Challen (1), Cangxiong Chen (4), Jing Chen (5), Joan Condell (3), Leon Danon (1), Adam Dennett (2), Alison Heppenstall (6), Paul Marshall (1), Phil Morgan (5), Aisling O'Kane (1), Laura G. E. Smith (4), Theresa Smith (4), Hywel T. P. Williams (7) ((1) University of Bristol, (2) University College London, (3) Ulster University, (4) University of Bath, (5) Cardiff University, (6) University of Glasgow, (7) University of Exeter) Seth Bullock (1)2024≈ 75%
- Meta-Reasoning: Semantics-Symbol Deconstruction for Large Language ModelsZhuosheng Zhang, Pei Zhang, Baosong Yang, Rui Wang Yiming Wang2024≈ 75%
- ≈ 74%
- ≈ 74%
- Tractable Uncertainty-Aware Meta-LearningCesar Almecija, Apoorva Sharma and Navid Azizan Young-Jin Park2026≈ 74%
- Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP ImaginationSongan Zhang, H. Eric Tseng, Huei Peng Lu Wen2023≈ 74%
- ≈ 71%
- Learning without neurons in physical systemsin corpus2022≈ 71%
- ≈ 70%
- ≈ 70%
- ≈ 70%
- The biogenic approach to cognitionin corpus2005≈ 69%
- The Platonic Representation Hypothesisin corpus2024≈ 69%
- ≈ 69%
- Collective intelligence: A unifying concept for integrating biology across scales and substratesin corpus2024≈ 68%
- The World Inside Neural Networksin corpus2026≈ 68%
- ≈ 68%
- Cognitive glues are shared models of relative scarcities: the economics of collective intelligencein corpus2026≈ 68%
- Active Inference, Curiosity and Insightin corpus2017≈ 68%