"One common mistake that I would make is adding a non-linearity to my logits output." What does the term "logit" means here or what does it represent ?
logit原本是一个函数，它是sigmoid函数（也叫标准logistic函数） p (x) = 1 1 + e x 的反函数： l o g i t (p) = log (p 1 p) 。 logit这个名字的来源即为 log istic un it。 但在深度学习中，logits就是最终的全连接层的输出，而非其本意。
这个维基 Logit - Wikipedia 上说的很清楚啦： The logit function is the inverse of the sigmoidal "logistic" function or logistic transform used in mathematics, especially in statistics. 最近看 Python Machine Learning，第三章中也介绍了logit与sigmoid，推荐题主一阅。
Here are few queries which are directly related to the purpose of logit function in Logistic regression modeling: Has Logit function (i.e. Logit equation LN (P/1-P)) being derived from Logistic Regression equation or its the other way around? What is the purpose of Logit equation in logistic regression equation?
