@inproceedings{780d9dba43cc4cd58e8c01155b3f1247,
title = "Guaranteed Quantization Error Computation for Neural Network Model Compression",
abstract = "Neural network model compression techniques can address the computation issue of deep neural networks on embedded devices in industrial systems. The guaranteed output error computation problem for neural network compression with quantization is addressed in this paper. A merged neural network is built from a feedforward neural network and its quantized version to produce the exact output difference between two neural networks. Then, optimization-based methods and reachability analysis methods are applied to the merged neural network to compute the guaranteed quantization error. Finally, a numerical example is proposed to validate the applicability and effectiveness of the proposed approach.",
keywords = "model compression, neural networks, quantization",
author = "Wesley Cooke and Zihao Mo and Weiming Xiang",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Conference on Industrial Technology, ICIT 2023 ; Conference date: 04-04-2023 Through 06-04-2023",
year = "2023",
doi = "10.1109/ICIT58465.2023.10143141",
language = "English (US)",
series = "Proceedings of the IEEE International Conference on Industrial Technology",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2023 IEEE International Conference on Industrial Technology, ICIT 2023",
}