Learnability with time-sharing computational resource concerns  

作　　者：Zhi-Hua Zhou 

机构地区：[1]National Key Laboratory for Novel Software Technology,Nanjing University,China

出　　处：《National Science Review》2024年第10期160-162,共3页国家科学评论（英文版）

基　　金：supported by the National Science and Technology Major Project(2022ZD0114800).

摘　　要：Conventional machine learning theories generally assume explicitly or implicitly that there are enough or even infinitely supplied computational resources such that all received data can be handled.In real practice,however,this is not the case.For example,in stream learning the incoming data streams can be potentially endless with overwhelming size and it is impractical to assume that all received data can be handled in time.Indeed,the performance of machine learning depends not only on how many data have been received,but also on how many data can be handled subject to the computational resource available;this is beyond the consideration of conventional learning theories.

关 键 词：HANDLE SUCH assume 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]