原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
The answer is memory. The recurrent feedback loops in an RNN are a kind of memory. They propagate information from timestep t to timestep t + 1. In other words, they remember information about timestep t when processing new information at timestep t + 1. Thus, by induction, an RNN can potentially remember information over arbitrarily long time intervals. In fact, RNNs are Turing complete:
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/c025.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8