For reasons that concern the implementation of floating point arithmetic, we decided to train our net with these twenty counts divided by a normalizing factor. 由于关注浮点运算的执行,我们打算用一种规格化因素将这20字符统计分开来,并以此培训我们的网络。
Normalizing: An Important Factor Influencing Heat Treatment Distortion of the Carburized Gears 正火&影响渗碳齿轮热处理畸变的一个重要因素