paper-with-me

홈 › Papers

An approach to reachability analysis for feed-forward ReLU neural networks

2017-06-22 · Alessio Lomuscio, Lalit Maganti

We study the reachability problem for systems implemented as feed-forward neural networks whose activation function is implemented via ReLU functions. We draw a correspondence between establishing whether some arbitrary output can ever be outputed by a neural system and linear problems characterising a neural system of interest. We present a methodology to solve cases of practical interest by means of a state-of-the-art linear programs solver. We evaluate the technique presented by discussing the experimental results obtained by analysing reachability properties for a number of benchmarks in the literature.

📄 PDF Abstract BibTeX arXiv:1706.07351

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Static analysis of ReLU neural networks with tropical polyhedra

2021-07-30 · Eric Goubault, Sébastien Palumby, Sylvie Putot, Louis Rustenholz 외

This paper studies the problem of range analysis for feedforward neural networks, which is a basic primitive for applications such as robustness of neural networks, compliance to specifications and reachability analysis …

Quadratic Characterizations for Reachability Analysis of Neural Networks

2026-05-19 · Elias Khalife, Mazen Farhood, Pierre-Loic Garoche arxiv

Quadratic constraints (QCs) are widely used to characterize nonlinearities and uncertainties, but generic analytical characterizations can be conservative on bounded domains. This paper develops a framework for construct…

Reachability analysis of neural networks using mixed monotonicity

2021-11-15 · Pierre-Jean Meyer

This paper presents a new reachability analysis approach to compute interval over-approximations of the output set of feedforward neural networks with input uncertainty. We adapt to neural networks an existing mixed-mono…

Hybrid Zonotopes Exactly Represent ReLU Neural Networks

2023-04-05 · Joshua Ortiz, Alyssa Vellucci, Justin Koeln, Justin Ruths

We show that hybrid zonotopes offer an equivalent representation of feed-forward fully connected neural networks with ReLU activation functions. Our approach demonstrates that the complexity of binary variables is equal …

The Reachability Problem for Neural-Network Control Systems

2024-07-06 · Christian Schilling, Martin Zimmermann

A control system consists of a plant component and a controller which periodically computes a control input for the plant. We consider systems where the controller is implemented by a feedforward neural network with ReLU…