We develop a novel framework to assess the risk of misperception in a traffic sign
classification task in the presence of exogenous noise. We consider the problem in an …

Digital predistortion (DPD) has proven to be an efficient method of linearizing power
amplifiers (PAs). In recent years, the use of neural networks (NNs) for DPD has gained …

For a given stable recurrent neural network (RNN) that is trained to perform a classification
task using sequential inputs, we quantify explicit robustness bounds as a function of …

With the advent of advanced perception algorithms, achieving long-term autonomy in
vehicle platooning has become a possibility. In this paper, we propose a framework to …

Uncertainty quantification is a critical yet unsolved challenge for deep learning, especially
for the time series imputation with irregularly sampled measurements. To tackle this …

Deep learning tools are now widely used across various areas due to the increasing interest
in applied machine learning. While these tools demonstrate exceptional performance in …

Networked control systems, rooted in networked control theory, tackle collective behavior
and coordination among interconnected entities. This concept, which is crucial in robotics …

This dissertation explores a diverse set of problems in dynamical systems, control,
estimation, and learning theory. Part I studies nonlinear systems using operator theory …

This study explores how attention mechanisms impact representation distributions within
neural networks, focusing on catastrophic forgetting and robustness to input noise. We …