In Proximity of ReLU DNN, PWA Function, and Explicit MPC
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Differentiable Nonlinear Model Predictive Control
Evaluating the Impact of Model Accuracy for Optimizing Battery Energy Storage Systems
Re4MPC: Reactive Nonlinear MPC for Multi-model Motion Planning via Deep Reinforcement Learning
Deep Operator Neural Network Model Predictive Control
Knot So Simple: A Minimalistic Environment for Spatial Reasoning
Efficient Configuration-Constrained Tube MPC via Variables Restriction and Template Selection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.