Back to course home
0% completed
Vote For New Content
5.3 Quiz
1. What is the primary role of hidden layers in a neural network?
A
They store the final model predictions.
B
They prevent any form of backpropagation.
C
They remove data points that don’t fit well.
D
They transform raw inputs into increasingly abstract representations, capturing complex patterns.
2. In backpropagation, what is the main purpose of the backward pass?
A
To randomize the weights after each forward pass.
B
To visualize how the model performs on the test set.
C
To calculate gradients that show how much each weight contributed to the error, and adjust them to minimize the loss.
D
To skip the training step and directly generate outputs.
3. Why is the ReLU (Rectified Linear Unit) activation function popular in deep networks?
A
It doesn’t allow neurons to output any negative values, simplifying computation and helping gradients flow better.
B
It’s the only function that avoids overfitting.
C
It’s always guaranteed to produce 100% accuracy.
D
It requires no hidden layers to function.
.....
.....
.....
Like the course? Get enrolled and start learning!
Table of Contents
Contents are not accessible
Contents are not accessible
Contents are not accessible
Contents are not accessible
Contents are not accessible