In Proximity of ReLU DNN, PWA Function, and Explicit MPC

Abstract

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.

arXiv commentSubmitted to Conference on Decision and Control (CDC) 2020

References in corpus (7)

• On the Number of Linear Regions of Deep Neural Networks
• Deep Knowledge Tracing
• Safe Model-based Reinforcement Learning with Stability Guarantees
• Efficient representation and approximation of model predictive control laws via deep learning
• On the number of response regions of deep feed forward networks with piece-wise linear activations
• Bounding and Counting Linear Regions of Deep Neural Networks
• Classification regions of deep neural networks