一句话：记录 Yedida 与 Menzies 在 TSE'21 论文中重用 Montufar 等人 ReLU 网络线性区域下界定理的证据。
本文记录了一项深度学习理论洞见在软件工程研究中的重用证据：Yedida 与 Menzies 在 TSE'21 论文中使用了 Montufar 等人关于带 ReLU 激活的前馈神经网络决策边界分段线性区域数量下界的结论。具体而言，作者文档化了该论文对 Montufar 等人定理 4 的重用。该工作属于可复现性与重用证据记录，并未提出新的神经网络理论或程序语言技术；它展示了深度学习理论结果如何被软件工程论文引用与复用，并保留其来源与使用方式。
We report here the reuse of theoretical insights from deep learning literature, used in a recent TSE '21 paper by Yedida & Menzies. The artifact replicated is the lower bound on the number of piecewise linear regions in the decision boundary of a feedforward neural network with ReLU activations, as studied by Montufar et al. We document the reuse of Theorem 4 from Montufar et al. by Yedida & Menzies.
DOI 原文 ·
@inproceedings{paperbot6428,
title = {Documenting evidence of a reuse of ‘on the number of linear regions of deep neural networks’},
author = {Rahul Yedida and Tim Menzies},
booktitle = {FSE},
year = {2021},
doi = {10.1145/3468264.3477213}
}