A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks
[article]
2022
arXiv
pre-print
Preserved Fulltext
In this work, we propose a novel and efficient formal verification approach for QNNs. ...
The resulting quantized neural networks (QNNs) can be implemented energy-efficiently. ...
ACKNOWLEDGMENTS This work is supported by the National Key Research Program (2020AAA0107800), National Natural Science Foundation of China (NSFC) under Grants Nos. 62072309 and 61872340, an oversea grant ...
arXiv:2212.11138v1
fatcat:6bgnww5uzfdzpcekicoktiq6li
Towards Efficient Verification of Quantized Neural Networks
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2023 pre-print arXiv:2312.12679v1 fatcat:mfdqe3cgdnfylgrq6wied5ypru
In this work, we propose a framework for formally verifying properties of quantized neural networks. ...
We evaluate our approach on perception networks quantized with PyTorch. ...
The baseline approach models neural networks and formal properties as integer linear programming (ILP) problems. ...
arXiv:2312.12679v2
fatcat:ku5i4e2vzzf7xkpupjbtk2kwu4