| 词条 | CLEVER score |
| 释义 |
}} The CLEVER (Cross Lipschitz Extreme Value for nEtwork Robustness) score is a way of measuring the robustness of an artificial neural network towards adversarial attacks.[1] It was developed by a team at the MIT-IBM Watson AI Lab and first presented at the 2018 International Conference on Learning Representations.[2] References1. ^{{cite arXiv |last=Weng |first=Tsui-Wei |date=2018 |title=Evaluating the robustness of neural networks: An extreme value theory approach |eprint=1801.10578}} {{Computer-science-stub}}2. ^{{cite web |url=https://www.ibm.com/blogs/research/2018/05/clever-adversarial-attack/ |title=A CLEVER Way to Resist Adversarial Attack |last= |first= |date=May 2, 2018 |website= |publisher= |access-date=September 12, 2018 |quote=}} 3 : Computer science|Deep learning|Artificial neural networks |
| 随便看 |
|
开放百科全书收录14589846条英语、德语、日语等多语种百科知识，基本涵盖了大多数领域的百科知识，是一部内容自由、开放的电子版国际百科全书。