Back to Search
Start Over
RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness
RobustNeuralNetworks.jl: a Package for Machine Learning and Data-Driven Control with Certified Robustness
- Publication Year :
- 2023
-
Abstract
- Neural networks are typically sensitive to small input perturbations, leading to unexpected or brittle behaviour. We present RobustNeuralNetworks.jl: a Julia package for neural network models that are constructed to naturally satisfy a set of user-defined robustness constraints. The package is based on the recently proposed Recurrent Equilibrium Network (REN) and Lipschitz-Bounded Deep Network (LBDN) model classes, and is designed to interface directly with Julia's most widely-used machine learning package, Flux.jl. We discuss the theory behind our model parameterization, give an overview of the package, and provide a tutorial demonstrating its use in image classification, reinforcement learning, and nonlinear state-observer design.
Details
- Database :
- arXiv
- Publication Type :
- Report
- Accession number :
- edsarx.2306.12612
- Document Type :
- Working Paper