计算机科学
布线(电子设计自动化)
障碍物
确定性
路由协议
路由域
人工智能
链路状态路由协议
地理路由
计算机网络
人工神经网络
深度学习
分布式计算
网络数据包
静态路由
机器学习
数学
几何学
法学
政治学
作者
Shihan Xiao,Haiyan Mao,Bo Wu,Wenjie Liu,Fenglin Li
标识
DOI:10.1145/3405671.3405813
摘要
Deep learning has shown great potential in automatically generating routing protocols for different optimization objectives. Although it may bring superior performance gains, there exists a fundamental obstacle to prevent existing network operators from deploying it into a real-world network, i.e., the uncertainty of statistical nature in deep learning can not provide the certainty of basic connectivity guarantee required in real-world routing.
科研通智能强力驱动
Strongly Powered by AbleSci AI