I am not clear why the test validation is checking for “linear” when the model that is being created is requiring for a binary classification which should be sigmoid. When I use sigmoid the test fails. Need clarification if this is a error in the notebook ? [sigmoid-linear]

[image] Pradeep_Nambiar: how will we satisfy this requirement that is asking for a binary classification Already answered - that’s what “from_logits = True” does.

Error in Lab notebook for Test Validation

Course Q&A Deep Learning Specialization Convolutional Neural Networks

paulinpaloalto December 21, 2023, 5:33pm 8

Yes, but that is wrong as Tom pointed out. Here’s a thread about why the from_logits = True mode is used when we are dealing with either binary or multiclass classifiers with cross entropy loss functions.

Topic		Replies	Views
Exercise 2 - alpaca_model (linear) Convolutional Neural Networks	2	593	August 16, 2023
Why don't I need to specify activation='sigmoid'? Convolutional Neural Networks	3	588	February 22, 2023
[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	757	April 19, 2021
Week 2, Assignment 2, Alpaca model: train vs validaton accuracy; linear vs sigmoid activationaccuracy Convolutional Neural Networks	6	594	July 11, 2021
Improved implementation of softmax - Neural network training \| Coursera Advanced Learning Algorithms week-2	1	60	June 25, 2024

Error in Lab notebook for Test Validation

Related topics