Also based on our explanation of logistic regression in Chapter 2, Data Modeling in Action - The Titanic Example, we are going to implement the logistic regression algorithm in TensorFlow. So, briefly, logistic regression passes the input through the logistic/sigmoid but then treats the result as a probability:
![](https://static.packt-cdn.com/products/9781788399906/graphics/assets/06e797f4-9584-46f6-8915-d1177426c2bb.png)
Figure 13: Discriminating between two linearly separable classes, 0's and 1's