我们团队在Microelectronics Reliability期刊上刚发表了一篇17页的研究论文，Title: Utilizing CNN to predict homogeneous thermo-mechanical properties of conductive layers for reliability numerical analysis in electronics。

Elsevier出版商给出了50天的任何人都可以免费下载全文的许可：

To help you access and share this work, we have created a Share Link – a personalized URL providing 50 days' free access to your article. Anyone clicking on this link before June 08, 2024 will be taken directly to the final version of your article on ScienceDirect, which they are welcome to read or download. No sign up, registration or fees are required.

https://authors.elsevier.com/a/1iyFe5%7EJAvJCb

该论文是2023年10月17日投稿的，审稿周期很长。实际上，在投稿后，我们团队用十种Transformer模型做了比较性的量化评估（AI样本是相同的），发现了很有趣的结果：某些Transformer模型能比这篇论文里的CNN模型取得预测精度更高、训练效率更高的结果；更加重要的是，所需样本数量可以很大幅度地减少，给人很大的惊喜，使得AI+IC更有产业应用可行性！