What neuroscience can tell AI about learning in continuously changing environments: perspectives
Modern artificial intelligence (AI) models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task and then deployed with fixed parameters. Their training is costly, slow and gradual, requiring billions of repetitions. In stark co...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
December 2025
|
| In: |
Nature machine intelligence
Year: 2025, Jahrgang: 7, Heft: 12, Pages: 1897-1912 |
| ISSN: | 2522-5839 |
| DOI: | 10.1038/s42256-025-01146-z |
| Online-Zugang: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1038/s42256-025-01146-z Verlag, lizenzpflichtig, Volltext: https://www.nature.com/articles/s42256-025-01146-z 
|
| Verfasserangaben: | Daniel Durstewitz, Bruno Averbeck & Georgia Koppe |
| Zusammenfassung: | Modern artificial intelligence (AI) models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task and then deployed with fixed parameters. Their training is costly, slow and gradual, requiring billions of repetitions. In stark contrast, animals continuously adapt to the ever-changing contingencies in their environments. This is particularly important for social species, where behavioural policies and reward outcomes may frequently change in interaction with peers. The underlying computational processes are often marked by rapid shifts in an animal’s behaviour and rather sudden transitions in neuronal population activity. Such computational capacities are of growing importance for AI systems operating in the real world, like those guiding robots or autonomous vehicles, or for agentic AI interacting with humans online. Can AI learn from neuroscience? This Perspective explores this question, integrating the literature on continual and in-context learning in AI with the neuroscience of learning on behavioural tasks with shifting rules, reward probabilities or outcomes. We outline an agenda for how the links between neuroscience and AI could be tightened, thus supporting the transfer of ideas and findings between both areas and contributing to the evolving field of NeuroAI. |
|---|---|
| Beschreibung: | Online veröffentlicht: 28. November 2025 Gesehen am 12.01.2026 |
| Beschreibung: | Online Resource |
| ISSN: | 2522-5839 |
| DOI: | 10.1038/s42256-025-01146-z |