AI 中文总结
研究神经人工智能中深度神经网络模型与大脑比较及趋同进化问题，通过证明两个最小DNN解在硬任务中的对齐特性，形式化逆变概念，指出强任务下网络比较度量选择不敏感且趋同进化或不可避免。
AI 中文摘要
在过去十五年中，神经人工智能的一系列结果引发了关于如何将深度神经网络（DNN）模型与大脑进行比较，以及人工网络与真实脑网络之间预期有多少趋同进化的核心问题。本文表明，对于任何两个解决足够困难任务的最小DNN解：（i）基于仿射映射的网络表示的“弱”对齐保证了特权轴的“强”对齐；（ii）对齐在网络层次结构中“拉链式”上升，导致从端到端任务优化中出现特权轴。这些结果形式化了Cao和Yamins [2024]中逆变的概念，并说明了对神经人工智能理论的重要影响：在足够强的任务下，网络间比较的度量选择并非那么敏感，并且趋同进化可能是不可避免的。
英文摘要
A series of results from the NeuroAI over the past fifteen years have raised core questions both about how to compare Deep Neural Network (DNN) models to the brain, and about how much convergent evolution to expect between artificial networks and real brain networks. Here, we show that for any two minimal DNN solutions to a sufficiently hard task: (i) "weak" alignment of network representations based on affine mappings guarantees "strong" alignment of privileged axes, and (ii) alignment "zippers" up the network hierarchy, causing the emergence of privileged axes from end-to-end task optimization. These results formalize the notion of contravariance from Cao and Yamins [2024], and illustrate important consequences for the theory of NeuroAI: with sufficiently strong tasks, choice of metric for inter-network comparison is not all that sensitive, and that convergent evolution is probably inevitable.
