wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Deep Learning - Q1

Total questions: 10

Worksheet time: 5mins

Name
Class
Date
1.

What is a neural network composed of?

python

a)

Layers, neurons, and weights

b)

Activation function only

c)

Bias terms only

d)

None of the options

2.

Which activation function is commonly used in hidden layers?

a)

Sigmoid

b)

ReLu

c)

TanH

d)

Softmax

3.

A multi-layer linear model is just a neural network without an activation function.

a)

True

b)

False

4.

In a multi-layer linear model without activation functions, the intermediate layers are redundant, thus, useless.

a)

True

b)

False

5.

What is the purpose of the `loss.backward()` function?

a)

To calculate loss

b)

To perform backpropagation

c)

To update weights

d)

To initialize gradients

6.

Choose the option that best describes what is happening in the code.

a)

Data preprocessing

b)

Model evaluation

c)

Model training

d)

Data augmentation

7.

Choose the options that are true about using non-linear functions in neural networks.

a)

Non-linear functions allow neural networks to model complex relationships.

b)

Non-linear functions reduce the need for multiple layers in a network.

c)

Without non-linear functions, a neural network behaves like a single-layer linear model.

d)

Using non-linear functions guarantees higher accuracy in every problem.

4o

8.

During training, you observe that the gradients are becoming extremely small. What might be the cause of this issue?

a)

The model is too large.

b)

This is due to vanishing gradients.

c)

The optimizer is not updating weights properly.

d)

The learning rate is too high.

9.

What is the primary function of the activation function in a neural network?

a)

To initialize weights

b)

To add non-linearity to the model

c)

To compute the gradients

d)

To reduce overfitting

10.

Which activation function is commonly used in the output layer for binary classification problems?

a)

Sigmoid

b)

Softmax

c)

Tanh

d)

ReLu