54 citations · 177 across the 51 of their papers we have counts for
7 papers · 1 filter
Safe-by-Design Learning via Energy-based Neural Networks
Simone Betteti, Morteza Lahijanian, Luca Laurenti
Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settings. Safety is commonly establi…
Universal Learning of Stochastic Dynamics for Exact Belief Propagation using Bernstein Normalizing Flows
Peter Amorese, Morteza Lahijanian
Predicting the distribution of future states in a stochastic system, known as belief propagation, is fundamental to reasoning under uncertainty. However, nonlinear dynamics often m…
Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs
Chun-Wei Kong, Luca Laurenti, Jay McMahon +1
Stochastic differential equations are commonly used to describe the evolution of stochastic processes. The state uncertainty of such processes is best represented by the probabilit…
Error Bounds For Gaussian Process Regression Under Bounded Support Noise With Applications To Safety Certification
Robert Reed, Luca Laurenti, Morteza Lahijanian
Gaussian Process Regression (GPR) is a powerful and elegant method for learning complex functions from noisy data with a wide range of applications, including in safety-critical do…
Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection
Steven Adams, Andrea Patanè, Morteza Lahijanian +1
Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of th…
Data-Driven Permissible Safe Control with Barrier Certificates
Rayan Mazouz, John Skovbekk, Frederik Baymler Mathiesen +3
This paper introduces a method of identifying a maximal set of safe strategies from data for stochastic systems with unknown dynamics using barrier certificates. The first step is…
BNN-DP: Robustness Certification of Bayesian Neural Networks via Dynamic Programming
Steven Adams, Andrea Patane, Morteza Lahijanian +1
In this paper, we introduce BNN-DP, an efficient algorithmic framework for analysis of adversarial robustness of Bayesian Neural Networks (BNNs). Given a compact set of input point…