We show that neural networks with absolute value activation function and with the path norm, the depth, the width and the network weights having logarithmic dependence on $1/\varepsilon$ can $\varepsilon$-approximate functions that are analytic on certain regions of $\mathbb{C}^d$.

翻译：我们显示,具有绝对值激活功能和路径规范、深度、宽度和网络重量的神经网络,如果对数依赖1美元/瓦列普西隆元,就能够在某些区域分析$\mathbb{C ⁇ d$的近似功能。