原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
Such a GAN may indeed learn the correct mapping from x to y values—that's one of the solutions that minimizes the loss—but there are many symmetries in this learning problem, that is, many different mappings achieve equivalent loss. For example, consider that we permute the mapping: if {x(i), y(i)} is the true mapping then consider we instead recover {x(i), y(i+1)} after learning (circularly shifting at
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c034.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8