原书出处
Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)
So, why not just normalize with the actual values—that is, using zj instead of ezj or, even easier, using arg maxj to set the highest value of z to 1 and leave the rest at 0? The reason is that each layer needs to remain differentiable for backpropagation to work. Yet the “brutal” cutoff introduced by the arg max function is exactly what we want
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