Nature Machine Intelligence:人工网络在多任务学习中自发形成模块化结构并与脑网络架构相似
摘要
Wu 等人的研究显示,学习多个任务的神经网络会组织成专门化的模块,在容量受限时尤为明显。增量式多任务学习会强化这种模块化,并产生与脑网络相似的架构。该研究发表于 Nature Machine Intelligence,DOI 为 10.1038/s42256-026-01306-9。
摘要由模型根据原文撰写,以原文为准。
正文 · 原文
Nature Machine Intelligence, Published online: 28 September 2026; doi:10.1038/s42256-026-01306-9
Wu et al. show that neural networks learning multiple tasks organize into specialized modules, particularly under capacity constraints. Incremental multitask learning strengthens this modularity and produces architectures resembling brain networks.
注意转载授权 · 阅读原文
来源:Nature Machine Intelligence · nature.com
引用原文
Yuhang Wu. Task-structured modularity emerges in artificial networks and aligns with brain architecture[EB/OL]. (2026-09-28)[访问日期]. https://www.nature.com/articles/s42256-026-01306-9.