原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
One common kind of recurrent layer is the Simple Recurrent Layer (SRN), which was defined by Elman in “Finding Structure in Time” [116]. For this layer, f is a linear layer followed by a pointwise nonlinearity, and g is another linear layer. The full computation is defined by the following equations:
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