A new research paper highlights how symmetries in network inputs can mislead representational similarity analyses (RSMs). These symmetries can make different network configurations appear functionally equivalent, yet produce distinct RSMs that reflect different representational geometries. The study demonstrates this issue in networks trained on image data, where latent symmetries can lead to sparse, drifting codes and consequently, drifting RSMs. The findings underscore the difficulties in comparing nonlinear neural codes when functionally equivalent representations are not simply rotational. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Highlights potential pitfalls in analyzing neural network representations, impacting research methodology.
RANK_REASON This is a research paper published on arXiv detailing a novel finding about representational similarity analyses. [lever_c_demoted from research: ic=1 ai=1.0]