arXiv cs.AI· S\'ilvia Garc\'ia-Hern\'andez, Leema Hamid, Manuel Brenner·· 13 小时前AI 评分26
100 项认知任务中循环动力学的多任务交互研究
Multitask Interactions in Recurrent Dynamics across 100 Cognitive Tasks
AI 导读
研究者在 100 项认知任务上同时训练分层 AL-RNN，发现性能随非线性容量和任务特征维度提升，联合分层模型优于单独训练模型和单一无结构联合模型。许多任务单独用线性动力学即可求解，却无法由共享线性模型共同解决。模型通过任务特征、线性区域使用和任务几何给出多种任务相似度度量，并关联任务复杂度、联合可解性、成对迁移学习与留一法适配。
正文 · 原文
Abstract:The brain continually learns tasks with very different computational demands. Recurrent neural networks (RNNs) have been used as dynamical surrogates for studying task solutions, with recent work extending this approach to joint training on multitask batteries. However, it remains unclear how tasks interact as these batteries grow in scale and heterogeneity: under what conditions do they transfer or interfere with one another, and how do these effects relate to task complexity and model structure? We study this question by simultaneously training hierarchical Almost-Linear RNNs (AL-RNNs) on 100 tasks spanning a wide range of cognitive demands. AL-RNNs allow us to vary the amount of nonlinearity in the recurrence, while hierarchical task features provide a low-dimensional interface for task-specific adaptation within shared dynamics. On this task battery, performance improves with both nonlinear capacity and task-feature dimensionality, with the joint hierarchical model outperforming both individually trained models and a single unstructured joint model. Many tasks are individually solvable with linear dynamics, yet cannot be solved together by a shared linear model. Through hierarchical task features, task-specific linear region usage, and task geometry, the trained model provides several related but distinct measures of task similarity that capture how computations are separated and combined within the shared backbone. Across a series of experiments, we relate these representations to individual task complexity, joint solvability, pairwise transfer learning, and leave-one-out adaptation. Together, our experiments characterize task interactions in multitask recurrent learning while demonstrating both the potential and the challenges of reusable dynamical backbones for cognitive computation.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2610.33926 [cs.LG] |
| (or arXiv:2610.33926v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33926 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sílvia García-Hernández [view email]
[v1]
Sat, 24 Oct 2026 21:38:06 UTC (6,829 KB)
来源：arXiv cs.AI · arxiv.org