Data Science Interview Questions: Why “Logits” in Deep Learning Cross-Entropy Loss?

March 27, 2020

In this Data Science Interview Questions series, we’re going to answer the question:

Why do deep learning libraries have functions like “softmax_cross_entropy_with_logits v2”?

Why can’t we just use the formulas we learned in class?

What do these functions do and how?

Click to watch the video below:

Go to comments


Deep Learning and Artificial Intelligence Newsletter

Get discount coupons, free machine learning material, and new course announcements