QVIP: An ILP-based formal verification approach for quantized neural networks

• Main Authors: ZHANG, Yedi, ZHAO, Zhe, CHEN, Guangke, SONG, Fu, ZHANG, Min, CHEN, Taolue, SUN, Jun
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Quantized neural network; formal verification; integer linear programming; robustness; OS and Networks; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/7281; https://ink.library.smu.edu.sg/context/sis_research/article/8284/viewcontent/ase22.pdf
• Institution: Singapore Management University

Deep learning has become a promising programming paradigm in software development, owing to its surprising performance in solving many challenging tasks. Deep neural networks (DNNs) are increasingly being deployed in practice, but are limited on resource-constrained devices owing to their demand for...