TensorFlow中logits一词的含义是什么?

问题描述

在以下TensorFlow函数中，我们必须在最后一层中提供人工神经元的激活.我了解.但是我不明白为什么叫logits?那不是数学函数吗?

In the following TensorFlow function, we must feed the activation of artificial neurons in the final layer. That I understand. But I don't understand why it is called logits? Isn't that a mathematical function?

loss_function = tf.nn.softmax_cross_entropy_with_logits(
     logits = last_layer,
     labels = target_output
)

推荐答案

登录是一个重载术语，可能意味着很多不同的东西:

Logits is an overloaded term which can mean many different things:

在数学中， Logit 是一种映射概率的函数( [0, 1])到R((-inf, inf))

In Math, Logit is a function that maps probabilities ([0, 1]) to R ((-inf, inf))

0.5的概率对应于0的对数.负的logit对应于小于0.5的概率，对大于0.5的正数.

Probability of 0.5 corresponds to a logit of 0. Negative logit correspond to probabilities less than 0.5, positive to > 0.5.

在ML 中，可以

也要登录 有时是指sigmoid函数的逐元素逆.

Logits also sometimes refer to the element-wise inverse of the sigmoid function.

这篇关于TensorFlow中logits一词的含义是什么?的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！