AI Chat AI Image Generator AI Video Text to Speech

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

06/09/2020

∙

by Saman Fahandezh-Saadi, et al.

∙

∙

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.

Saman Fahandezh-Saadi
5 publications
Masayoshi Tomizuka
149 publications

research

∙ 11/05/2019

AReN: Assured ReLU NN Architecture for Model Predictive Control of LTI Systems

In this paper, we consider the problem of automatically designing a Rect...

0 James Ferlez, et al. ∙

research

∙ 11/04/2016

Understanding Deep Neural Networks with Rectified Linear Units

In this paper we investigate the family of functions representable by de...

0 Raman Arora, et al. ∙

research

∙ 07/29/2022

Spline Representation and Redundancies of One-Dimensional ReLU Neural Network Models

We analyze the structure of a one-dimensional deep ReLU neural network (...

0 Gerlind Plonka, et al. ∙

research

∙ 12/07/2021

Tailored neural networks for learning optimal value functions in MPC

Learning-based predictive control is a promising alternative to optimiza...

0 Dieter Teichrib, et al. ∙

research

∙ 05/18/2021

ReLU Deep Neural Networks and linear Finite Elements

In this paper, we investigate the relationship between deep neural netwo...

0 Juncai He, et al. ∙

research

∙ 10/01/2021

Error-free approximation of explicit linear MPC through lattice piecewise affine expression

In this paper, the disjunctive and conjunctive lattice piecewise affine ...

0 Jun Xu, et al. ∙

research

∙ 05/18/2022

Bridging the gap between QP-based and MPC-based RL

Reinforcement learning methods typically use Deep Neural Networks to app...

0 Shambhuraj Sawant, et al. ∙