发表机构
Great Bay University(大湾区大学)
机构由 AI 辅助整理,请以论文原文为准。AI 中文总结
本文通过一个可手工验证的六边形恒等式,解析证明了两个隐藏 ReLU 层足以计算六个数的最大值,并给出了宽度为 17 和 41 的显式网络。
AI 中文摘要
精确计算最大值函数是研究 ReLU 网络深度的一个标准测试用例。已知通过计算机辅助构造,两个隐藏层足以处理多达十二个输入。对于六个实数输入,我们给出了一个显式的六边形恒等式,其局部结构产生了一个自包含的解析证明,证明了这一深度界限。该恒等式是通过计算机辅助搜索发现的;我们通过显式的消去来证明它,这些消去可以完全手工检查,无需执行验证程序。该恒等式还产生了一个显式的网络,其隐藏宽度为 $17$ 和 $41$,零偏置和有理权重。
英文摘要
Exactly computing the maximum function is a standard test case for studying depth in ReLU networks. Two hidden layers are known to suffice for up to twelve inputs through computer-assisted constructions. For six real inputs, we give an explicit hexagon identity whose local structure yields a self-contained analytical proof of this depth bound. The identity was found by computer-assisted search; we prove it through explicit cancellations that can be checked entirely by hand, without executing a verification program. The identity also yields an explicit network with hidden widths $17$ and $41$, zero biases, and rational weights.
Comments14 pages