Searched for: author%3A%22Lahijanian%2C+Morteza%22
(1 - 6 of 6)
document
Delimpaltadakis, Giannis (author), Lahijanian, Morteza (author), Mazo, M. (author), Laurenti, L. (author)
Interval Markov Decision Processes (IMDPs) are finite-state uncertain Markov models, where the transition probabilities belong to intervals. Recently, there has been a surge of research on employing IMDPs as abstractions of stochastic systems for control synthesis. However, due to the absence of algorithms for synthesis over IMDPs with...
conference paper 2023
document
Skovbekk, John (author), Laurenti, L. (author), Frew, Eric (author), Lahijanian, Morteza (author)
Verifying the performance of safety-critical, stochastic systems with complex noise distributions is difficult. We introduce a general procedure for the finite abstraction of nonlinear stochastic systems with nonstandard (e.g., non-affine, non-symmetric, non-unimodal) noise distributions for verification purposes. The method uses a finite...
journal article 2023
document
Adams, S.J.L. (author), Patanè, Andrea (author), Lahijanian, Morteza (author), Laurenti, L. (author)
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 points T ⊂ R<sup>n</sup>, BNN-DP computes lower and upper bounds on the BNN's predictions for all the points in T. The framework is based on an interpretation of BNNs as...
conference paper 2023
document
Reed, Robert (author), Laurenti, L. (author), Lahijanian, Morteza (author)
Deep Kernel Learning (DKL) combines the representational power of neural networks with the uncertainty quantification of Gaussian Processes. Hence, it is potentially a promising tool to learn and control complex dynamical systems. In this letter, we develop a scalable abstraction-based framework that enables the use of DKL for control...
journal article 2023
document
Adams, S.J.L. (author), Lahijanian, Morteza (author), Laurenti, L. (author)
Neural networks (NNs) are emerging as powerful tools to represent the dynamics of control systems with complicated physics or black-box components. Due to complexity of NNs, however, existing methods are unable to synthesize complex behaviors with guarantees for NN dynamic models (NNDMs). This letter introduces a control synthesis framework for...
journal article 2022
document
Jackson, John (author), Laurenti, L. (author), Frew, Eric (author), Lahijanian, Morteza (author)
We present a data-driven framework for strategy synthesis for partially-known switched stochastic systems. The properties of the system are specified using linear temporal logic (LTL) over finite traces (LTLf), which is as expressive as LTL and enables interpretations over finite behaviors. The framework first learns the unknown dynamics via...
conference paper 2021
Searched for: author%3A%22Lahijanian%2C+Morteza%22
(1 - 6 of 6)