原书出处
Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)
Although the max() function is not differentiable, MaxPooling can still be used in backpropagation by selectively passing the gradient to only the neuron that has shown to have the maximum activation and setting the gradient of all other neurons to zero. When an averaging pooling function is used, the gradient is divided among all neurons in the pool in equal parts.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)/_epub-src/OEBPS/xhtml/chapter_10.xhtml
EPUB SHA-256:e922df804e4bed095a1b85e46ce7c83343b1af42a95fdc39ac9ab4a47b42acb1