论文标题
在Relu DNN，PWA功能和显式MPC的接近度上
In Proximity of ReLU DNN, PWA Function, and Explicit MPC
论文作者
论文摘要
分析了整流器（Relu）深神经网络（DNN）及其与分段仿射（PWA）功能的连接。该论文是为了找到并研究代表模型预测控制（MPC）的明确反馈政策的可能性，反之亦然。 DNN的复杂性和结构已通过一些定理和讨论进行了研究。已经开发了一种近似方法来识别Relu Net中的输入空间，从而导致多面体区域的PWA功能。同样，已经研究了逆多参数线性或二次程序（MP-LP或MP-QP），该程序处理了PWA函数的重建和成本函数的重建。
Rectifier (ReLU) deep neural networks (DNN) and their connection with piecewise affine (PWA) functions is analyzed. The paper is an effort to find and study the possibility of representing explicit state feedback policy of model predictive control (MPC) as a ReLU DNN, and vice versa. The complexity and architecture of DNN has been examined through some theorems and discussions. An approximate method has been developed for identification of input-space in ReLU net which results a PWA function over polyhedral regions. Also, inverse multiparametric linear or quadratic programs (mp-LP or mp-QP) has been studied which deals with reconstruction of constraints and cost function given a PWA function.
