认知图的相对表示
Relative representations for cognitive graphs
AI总结:
本文将相对表示扩展至离散状态空间模型,利用克隆结构认知图(CSCGs)实现跨智能体通信,并提出一种事后应用的零样本模型拼接技术,为认知地图研究提供概念验证。
摘要:
尽管不同神经网络学习到的潜在空间通常无法直接比较,但机器学习领域的近期工作表明,可以利用潜在空间向量之间的相似性和差异来推导出“相对表示”,其表示能力与“绝对”对应物相当,并且在基于相似数据分布训练的模型中几乎完全相同。除了在揭示学习到的潜在空间底层结构方面具有内在价值外,相对表示还可用于跨网络比较表示,作为收敛的通用代理,以及用于零样本模型拼接。在这项工作中,我们研究了相对表示向离散状态空间模型的扩展,使用用于二维空间定位和导航的克隆结构认知图(Clone-Structured Cognitive Graphs, CSCGs)作为测试案例。我们的工作表明,在消息传递过程中计算的概率向量可用于定义CSCGs上的相对表示,从而实现了在使用不同随机初始化和训练序列训练的智能体之间,以及仅在部分相似的空间上的有效通信。我们引入了一种零样本模型拼接技术,该技术可以事后应用,而无需在训练期间使用相对表示。这项探索性工作旨在作为将相对表示应用于神经科学和人工智能中认知地图研究的概念验证。
英文摘要:
Although the latent spaces learned by distinct neural networks are not generally directly comparable, recent work in machine learning has shown that it is possible to use the similarities and differences among latent space vectors to derive "relative representations" with comparable representational power to their "absolute" counterparts, and which are nearly identical across models trained on similar data distributions. Apart from their intrinsic interest in revealing the underlying structure of learned latent spaces, relative representations are useful to compare representations across networks as a generic proxy for convergence, and for zero-shot model stitching. In this work we examine an extension of relative representations to discrete state-space models, using Clone-Structured Cognitive Graphs (CSCGs) for 2D spatial localization and navigation as a test case. Our work shows that the probability vectors computed during message passing can be used to define relative representations on CSCGs, enabling effective communication across agents trained using different random initializations and training sequences, and on only partially similar spaces. We introduce a technique for zero-shot model stitching that can be applied post hoc, without the need for using relative representations during training. This exploratory work is intended as a proof-of-concept for the application of relative representations to the study of cognitive maps in neuroscience and AI.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。