互易性可使机械网络的学习能力减半
Reciprocity can halve what a mechanical network can learn
浏览论文内容
中文总结 AI 辅助
该研究指出无源线性弹性机械网络的麦克斯韦-贝蒂互易性会使其学习能力减半，实验验证了优化器和对比规则的误差表现，奇耦合可恢复丢失方向但需外部扭矩源。
中文摘要 AI 辅助
可调控机械网络正被开发为就地学习的材料，其容量通过与目标约束相对的可调控参数数量估算，忽略了麦克斯韦-贝蒂互易性——所有无源线性弹性网络天生具有的对称性。当p个自由度同时被驱动和读出时，无论网络的大小、拓扑结构和刚度如何，每个可达响应块都位于余维数为p(p-1)/2的子空间中；在完全重叠时，近一半的目标空间无法到达。这对训练的影响是一个数值：任何学习规则留下的误差至少是目标在共享自由度上反对称部分的范数，可在训练前计算，而正定性会增加一个正交第二项。使用精确雅可比矩阵的二阶优化器在144次运行中的143次达到该下限，键局部对比规则在24次运行中的22次达到0.1%以内的误差，而奇耦合则以外部扭矩源为代价恢复了丢失的方向：网络变为有源。规定位移驱动遵循我们证明的配套定律。该对称性是经典的，其对具有有限可调控刚度的固定图在部分重叠时的影响是新的。对于已发表的机器人超材料，它表明没有对称正定刚度矩阵能满足其沉积数据整合的线性模型中的两个目标。
英文摘要
A passive, reciprocal, linear network driven by forces or currents and read at points it drives cannot be trained below an error floor computed from the target beforehand. The usual parameter count for such networks does not charge for Maxwell-Betti reciprocity. We prove that when such an elastic, resistor or flow network has a symmetric response operator and p driven degrees of freedom are also read, its reachable response blocks lie in a subspace of codimension p(p-1)/2, whatever its size and topology, and the floor is the distance to it. On targets with a reachable symmetric part, a second-order optimiser ends within 0.1% of the floor in 142 of 144 simulated runs, and a contrastive rule with a bond-local update direction, within its step budget, in 22 of 24. Reciprocity charges a list of single drive-read tasks only for the pairs it instruments in both directions, and a rank test on the passive network says in advance whether, and on which bonds, odd couplings locally restore the lost directions, at a cost in non-reciprocity that the target bounds from below. Under an imposed-displacement drive, the one most physical-learning hardware uses, reciprocity survives as a weaker law, an exact balance between forward and reverse transmissions once each is weighted by the driving-point compliance at its input, and an inequality on their product, under which no symmetric positive-definite chain meets both targets of a published robotic metamaterial. All nineteen published layouts we tabulated pay nothing; a force-driven layout that asks one pair to respond differently in its two directions will.
发表机构
- Hanoi University of Civil Engineering（河内土木工程大学）
- National University of Laos（老挝国立大学）
- University of Transport and Communications（交通通信大学）
机构由 AI 辅助整理，请以论文原文为准。
