原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
Autoregressive models (section 32.7) are already modeling a sequence of conditional distributions. So, to condition them on some inputs x, we can simply concatenate x as a prefix to the sequence of y values we are modeling, yielding the new sequence: [x1, …, xm, y1, …, yn]. The probability model factorizes as:
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