Kaur, Ramneet

Email Address
Research Projects
Organizational Units
Research Interests

Search Results

Now showing 1 - 3 of 3
  • Publication
    Detecting OODs as datapoints with High Uncertainty
    (2021-07-23) Kaur, Ramneet; Park, Sangdon; Sokolsky, Oleg; Jha, Susmit; Lee, Insup; Roy, Anirban
    Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution inputs (OODs). This limitation is one of the key challenges in the adoption of DNNs in high-assurance systems such as autonomous driving, air traffic management, and medical diagnosis. This challenge has received significant attention recently, and several techniques have been developed to detect inputs where the model’s prediction cannot be trusted. These techniques detect OODs as datapoints with either high epistemic uncertainty or high aleatoric uncertainty. We demonstrate the difference in the detection ability of these techniques and propose an ensemble approach for detection of OODs as datapoints with high uncertainty (epistemic or aleatoric). We perform experiments on vision datasets with multiple DNN architectures, achieving state-of-the-art results in most cases.
  • Publication
    Parameter Invariant Monitoring for Signal Temporal Logic
    (2018-04-01) Roohi, Nima; Kaur, Ramneet; Weimer, James; Sokolsky, Oleg; Lee, Insup
    Signal Temporal Logic (STL) is a prominent specification formalism for real-time systems, and monitoring these specifications, specially when (for different reasons such as learning) behavior of systems can change over time, is quite important. There are three main challenges in this area: (1) full observation of system state is not possible due to noise or nuisance parameters, (2) the whole execution is not available during the monitoring, and (3) computational complexity of monitoring continuous time signals is very high. Although, each of these challenges has been addressed by different works, to the best of our knowledge, no one has addressed them all together. In this paper, we show how to extend any parameter invariant test procedure for single points in time to a parameter invariant test procedure for efficiently monitoring continuous time executions of a system against STL properties. We also show, how to extend probabilistic error guarantee of the input test procedure to a probabilistic error guarantee for the constructed test procedure.
  • Publication
    Runtime verification of parametric properties using SMEDL
    (2019-09-01) Zhang, Teng; Kaur, Ramneet; Lee, Insup; Sokolsky, Oleg
    Parametric properties are typical properties to be checked in runtime verification (RV). As a common technique for parametric monitoring, trace slicing divides an execution trace into a set of sub traces which are checked against non-parametric base properties. An efficient trace slicing algorithm is implemented in MOP. Another RV technique, QEA further allows for nested use of universal and existential quantification over parameters. In this paper, we present a methodology for parametric monitoring using the RV framework SMEDL. Trace slicing algorithm in MOP can be expressed by execution of a set of SMEDL monitors. Moreover, the semantics of nested quantifiers is encoded by a hierarchy of monitors for aggregating verdicts of sub traces. Through case studies, we demonstrate that SMEDL provides a natural way to monitor parametric properties with more potentials for flexible deployment and optimizations.