一句话：该工作将LSTM循环神经网络及改进结构用于软件系统可靠性建模，并在四个工业项目数据上初步评估。
本文研究如何用神经网络对软件系统可靠性进行建模。方法上采用带长短期记忆（LSTM）单元的循环神经网络与截断反向传播算法，并使用编码器-解码器LSTM架构；作者还提出两类变体：将软件可靠性函数作为LSTM的激活函数，以及将软件可靠性函数的输出作为LSTM输入特征。摘要报告了来自4个工业项目数据的初步评估，但未给出具体数值结果。
This work models the reliability of software systems using recurrent neural networks with long short-term memory (LSTM) units and truncated backpropagation algorithm, and encoder-decoder LSTM architecture and proposes LSTM with software reliability functions as activation functions and LSTM with input features as the output of software reliability functions. An initial evaluation on data coming from 4 industrial projects is also provided.
DOI 原文 ·
@inproceedings{paperbot4587,
title = {On the adoption of neural networks in modeling software reliability},
author = {Kamill Gusmanov},
booktitle = {FSE},
year = {2018},
doi = {10.1145/3236024.3275433}
}