arXiv：cs.LG· Farhad Pashakhanloo, Jacob A. Zavatone-Veth·· 5 小时前AI 评分36
刺激对称性会干扰表征相似性分析（RSM）
Stimulus symmetries can confound representational similarity analyses
AI 导读
研究发现，网络输入中的对称性会使许多表征在功能上等价，却产生不同的表征相似性矩阵（RSM），对应从解耦到最大混合等性质不同的表征几何。随机梯度下降或能量正则化可生成稀疏、漂移的编码，进而导致 RSM 漂移，该现象在训练于图像数据的网络（对称性为隐式）中同样存在。
正文
Abstract:What can representational similarity matrices (RSMs) tell us about a neural code? As the popularity of these summary statistics grows, so too does the need for a more complete characterization of their properties. Here, we show that symmetries in network inputs can confound RSM-based analyses. Stimulus symmetries render many representations functionally equivalent, but these different configurations can lead to different RSMs. These different RSMs reflect qualitatively different representational geometries, ranging from disentangled to maximally-mixed codes. We show that stochastic gradient descent or energetic regularization can generate sparse, drifting codes, leading in turn to drifting RSMs. Moreover, we demonstrate that these phenomena are present in networks trained to encode image data, where the symmetry is latent. Our results illustrate the challenges inherent in comparing nonlinear neural codes, when functionally-equivalent representations are not related by a simple rotation.
| Comments: | 17+25 pages, 8+12 figures |
| Subjects: | Neurons and Cognition (q-bio.NC); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.21324 [q-bio.NC] |
| (or arXiv:2605.21324v2 [q-bio.NC] for this version) | |
| https://doi.org/10.48550/arXiv.2605.21324 arXiv-issued DOI via DataCite |
Submission history
From: Jacob Zavatone-Veth [view email]
[v1]
Wed, 20 May 2026 15:51:21 UTC (10,006 KB)
[v2]
Fri, 2 Oct 2026 13:41:19 UTC (9,684 KB)
来源：arXiv：cs.LG · arxiv.org