The impressive capabilities of deep neural networks have inspired system developers to use them in safety-critical cyber-physical control systems, such as autonomous vehicles and air traffic collision avoidance systems. For such applications it is imperative that the correctness of DNN systems be verified. Furthermore, it is desirable that such systems be resistant to perturbations introduced by an adversary, or by inadvertent data corruption from system noise, domain shift, or broken sensors. Several recent incidents have underscored the need to better understand DNNs and verify both their safety and security.
This project aims at developing techniques for analysis of DNNs by combining methods from formal methods, cyber-physical systems, and robotics. We are seeking candidates who have demonstrated ability to lead and/or work collaboratively in teams comprised of individuals of diverse backgrounds, skills, and perspectives.
This position involves algorithm development, prototype implementations, and possibly hands-on work with robotic platforms to demonstrate the results.
Position Status: Full-Time
Rice University is an Equal Opportunity Employer with commitment to diversity at all levels, and considers for employment qualified applicants without regard to race, color, religion, age, sexual orientation, gender identity, national or ethnic origin, genetic information, disability or protected veteran status.
Internal Number: 26041
About Rice University
As a leading research university with a distinctive commitment to undergraduate education, Rice University aspires to pathbreaking research, unsurpassed teaching and contributions to the betterment of our world. It seeks to fulfill this mission by cultivating a diverse community of learning and discovery that produces leaders across the spectrum of human endeavor.