摘要:
Informally,wedenethebiasofamodeltobetheexpected generalizationerrorevenifweweretofitittoavery(say,innitely)large trainingset.Thus,fortheproblemabove,thelinearmodelsuersfromlarge bias,andmayundert(i.e.,failtocapturestructureexhibitedby)thedata. Apartfrombias,there'sasecondcomponenttothegeneraliza 阅读全文
posted @ 2013-06-24 15:06
FancyDRY
阅读(247)
评论(0)
推荐(0)
浙公网安备 33010602011771号