Neural Network Verification: an Interview with Taylor Johnson, Vanderbilt Computer Science скачать в хорошем качестве

Neural Network Verification: an Interview with Taylor Johnson, Vanderbilt Computer Science

How do we verify the output of a neural network? Taylor Johnson is an Associate Professor of Computer Science at Vanderbilt University and discusses this line of work. 00:00 Introduction 05:06 What is verification 08:30 Challenges of neural network verification 14:43 Verification techniques to measure neural network robustness 29:15 Application to security 33:11 Neurosymbolic AI and verification 37:00 Taylor's advice on the future of the field Links to papers and software: https://conf.researchr.org/details/Fo... https://link.springer.com/chapter/10.... https://github.com/verivital/nnv The Neuro Symbolic Channel provides the tutorials, courses, and research results on one of the most exciting areas in artificial intelligence and machine learning. With content originally from the AI course taught at Arizona State University, this channel brings you the latest at the intersection of symbolic methods (e.g., logic programming) and deep learning. Learn about the latest algorithms, Python packages, and progress toward larger goals such as artificial general intelligence (AGI).