Skip to main content

and
  1. Article

    Generating probabilistic safety guarantees for neural network controllers

    Neural networks serve as effective controllers in a variety of complex settings due to their ability to represent expressive policies. The complex nature of neural networks, however, makes their output difficu...

    Sydney M. Katz, Kyle D. Julian, Christopher A. Strong in Machine Learning (2023)

  2. No Access

    Chapter and Conference Paper

    ZoPE: A Fast Optimizer for ReLU Networks with Low-Dimensional Inputs

    Deep neural networks often lack the safety and robustness guarantees needed to be deployed in safety critical systems. Formal verification techniques can be used to prove input-output safety properties of netw...

    Christopher A. Strong, Sydney M. Katz, Anthony L. Corso in NASA Formal Methods (2022)