Assignment Transfer_learning_with_MobileNet_v1: For binary classification, we use the sigmoid (or softmax for 3 or more outputs). Why do we use the linear activation in the prediction layer of the model ? Thanks, Vu

Alcapa_model: why not sigmoid at prediction?

paulinpaloalto April 23, 2021, 2:36pm 2

The sigmoid is there: it’s just hidden in the loss function call that they use there. Here’s another recent thread about the same question.

1 Like

Topic		Replies	Views
Transfer_learning_with_MobileNet: Convolutional Neural Networks	1	497	November 22, 2021
Exercise 2 - alpaca_model (linear) Convolutional Neural Networks	2	594	August 16, 2023
Week2- programming assignment- mobile net- activation funcation Convolutional Neural Networks	2	538	November 3, 2021
[Week 2] Assignment 2, Exercise 2 : Why should we choose 'linear' output instead of sigmoid output if it's binary classification problem and not linear regression? Convolutional Neural Networks	1	758	April 19, 2021
C4 W2 Exercise 2 Convolutional Neural Networks	1	494	October 3, 2022