3 papers
cs.LG2024
Self-Satisfied: An end-to-end framework for SAT generation and prediction
Christopher R. Serrano, Jonathan Gallagher, Kenji Yamada +2
The boolean satisfiability (SAT) problem asks whether there exists an assignment of boolean values to the variables of an arbitrary boolean formula making the formula evaluate to T…
cs.LG2020
Generate and Verify: Semantically Meaningful Formal Analysis of Neural Network Perception Systems
Chris R. Serrano, Pape M. Sylla, Michael A. Warren
Testing remains the primary method to evaluate the accuracy of neural network perception systems. Prior work on the formal verification of neural network perception models has been…
cs.LG2019
Introspection Learning
Chris R. Serrano, Michael A. Warren
Traditional reinforcement learning agents learn from experience, past or present, gained through interaction with their environment. Our approach synthesizes experience, without re…