no code implementations • 25 Jul 2023 • Michael Yuhas, Arvind Easwaran
We consider an LEC with binary output like an autonomous emergency braking system (AEBS) and use risk, the combination of severity and occurrence of a failure, to model the effect of both components' design parameters on each other's functional and non-functional performance, as well as their impact on system safety.
no code implementations • 4 Apr 2023 • Mohit Prashant, Arvind Easwaran
To distinguish between OOD data and data known to the learning component through the training process, an emerging technique is to incorporate variational autoencoders (VAE) within systems and apply classification or anomaly detection techniques on their latent spaces.
1 code implementation • 15 Nov 2022 • Michael Yuhas, Arvind Easwaran
In a cyber-physical system such as an autonomous vehicle (AV), machine learning (ML) models can be used to navigate and identify objects that may interfere with the vehicle's operation.
no code implementations • 18 Oct 2022 • Zahra Rahiminasab, Michael Yuhas, Arvind Easwaran
Our framework consists of three steps: partitioning data based on observed generative factors, training a VAE as a logic tensor network that satisfies disentanglement rules, and run-time OOD reasoning.
no code implementations • 23 Aug 2022 • Archit Gupta, Arvind Easwaran
Duckiebots are low-cost mobile robots that are widely used in the fields of research and education.
1 code implementation • 29 Jul 2022 • Michael Yuhas, Daniel Jun Xian Ng, Arvind Easwaran
Insights into the trade-offs that occur during the design process are provided, and it is shown that this design methodology can lead to a drastic reduction in response time in relation to an unoptimized OOD detector while maintaining comparable accuracy.
no code implementations • 26 Aug 2021 • Shreyas Ramakrishna, Zahra Rahiminasab, Gabor Karsai, Arvind Easwaran, Abhishek Dubey
In this paper, we study this problem as a multi-labeled time series OOD detection problem over images, where the OOD is defined both sequentially across short time windows (change points) as well as across the training data distribution.
Out-of-Distribution Detection Out of Distribution (OOD) Detection +1
1 code implementation • 25 Jul 2021 • Yeli Feng, Daniel Jun Xian Ng, Arvind Easwaran
Uncertainties in machine learning are a significant roadblock for its application in safety-critical cyber-physical systems (CPS).
no code implementations • 25 Jul 2021 • Yeli Feng, Arvind Easwaran
Highly complex deep learning models are increasingly integrated into modern cyber-physical systems (CPS), many of which have strict safety requirements.
no code implementations • 17 Jul 2020 • Bai Xue, Miaomiao Zhang, Arvind Easwaran, Qin Li
In this paper we present a novel model checking approach to finite-time safety verification of black-box continuous-time dynamical systems within the framework of probably approximately correct (PAC) learning.
Systems and Control Formal Languages and Automata Theory Systems and Control
no code implementations • 10 Mar 2020 • Vijaya Kumar Sundar, Shreyas Ramakrishna, Zahra Rahiminasab, Arvind Easwaran, Abhishek Dubey
We use the fact that compact latent space generated by an appropriately selected $\beta$-VAE will encode the information about these factors in a few latent variables, and that can be used for computationally inexpensive detection.
no code implementations • 11 Sep 2019 • Xiaozhe Gu, Arvind Easwaran
As pointed in [17], ML models work well in the "training space" (i. e., feature space with sufficient training data), but they could not extrapolate beyond the training space.