Zijiang Yang

TL;DR: This work designs and implements a deep learning approach to model an elastic homogenization structure-property linkage in a high contrast composite material system and demonstrates that this end-to-end framework can predict the effective stiffness of high contrast elastic composites with a wide of range of microstructures, while exhibiting high accuracy and low computational cost for new evaluations.

TL;DR: In this paper, a system and method for formal verification of software that advantageously translates the software, which can have bounded recursion, into a Boolean representation (130) comprised of basic blocks and which applies SAT-based model checking (150) to the Boolean representation.

TL;DR: This work presents a deep adversarial learning methodology that overcomes the limitations of existing MCR techniques and provides an end-to-end solution for microstructural materials design, in which GAN reduces information loss and preserves more microStructural characteristics, and the GP-Hedge optimization improves the efficiency of design exploration.

TL;DR: This work uses the proofanalysis technique with SAT-based BMC, in order to generate effective abstract models and demonstrates the effectiveness of the prototype implementation on several large industry designs.

TL;DR: The verification tool F-Soft is described, which is developed for the analysis of C programs and its novelty lies in the combination of several recent advances in formal verification research including SAT-based verification, static analyses and predicate abstraction.