arXiv：cs.LG· Dom CP Marticorena, Chris Wissmann, Zeyu Lu, Dennis L Barbour·· 13 小时前
多维贝叶斯主动机器学习用于工作记忆任务表现评估
Multidimensional Bayesian Active Machine Learning of Working Memory Task Performance
AI 导读
研究者在沉浸式虚拟测试环境中验证了一种贝叶斯双轴主动分类方法，用于5×5空间工作记忆重建任务，同时控制空间负载L（占用格子数）和特征绑定负载K（不同颜色数），以非参数高斯过程（GP）概率分类器的后验不确定性引导刺激采集。
正文
Abstract:While adaptive experimental design has outgrown one-dimensional, staircase-based adaptations, most cognitive experiments still control a single factor and summarize performance with a scalar. In contrast, we validate here a Bayesian, two-axis, active-classification approach in an immersive virtual testing environment, using a 5-by-5 spatial working-memory reconstruction task as an application domain. Two variables are controlled: spatial load L (number of occupied tiles) and feature-binding load K (number of distinct colors) of items. Stimulus acquisition is guided by posterior uncertainty of a nonparametric Gaussian Process (GP) probabilistic classifier, which outputs a surface over (L, K) rather than a single threshold or maximum span value. In a young adult population, we compare GP-driven Adaptive Mode (AM) with a traditional adaptive staircase Classic Mode (CM), which varies L only at K = 3. Parity between the methods is achieved for this cohort, with an intraclass correlation coefficient of 0.755 at K = 3. As a secondary exploratory result, AM reveals individual differences in interactions between spatial load and feature binding. AM estimates converge more quickly than other sampling strategies, demonstrating that only about 30 samples are required for accurate fitting of the full model.
| Comments: | 42 pages, 7 figures |
| Subjects: | Machine Learning (cs.LG); Human-Computer Interaction (cs.HC) |
| Cite as: | arXiv:2510.00375 [cs.LG] |
| (or arXiv:2510.00375v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2510.00375 arXiv-issued DOI via DataCite |
Submission history
From: Dennis Barbour [view email]
[v1]
Wed, 1 Oct 2025 00:48:14 UTC (2,530 KB)
[v2]
Thu, 11 Jun 2026 20:47:23 UTC (2,542 KB)
[v3]
Fri, 9 Oct 2026 12:10:31 UTC (6,848 KB)
来源：arXiv：cs.LG · arxiv.org