wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

Artificial Neural Networks (Part 1- Part 3) Quiz

Total questions: 20

Worksheet time: 10mins

Name
Class
Date
1.

What does the input layer of an ANN contain?

a)

Neurons

b)

Bias values

c)

Input variables

d)

Transfer functions

2.

Which layer in ANN makes the final prediction?

a)

Input layer

b)

Hidden layer

c)

Output layer

d)

Training layer

3.

What is the purpose of a hidden layer in ANN?

a)

Collect raw input

b)

Make final decisions

c)

Perform internal processing

d)

Display results

4.

Which of the following is NOT part of a neuron?

a)

Weight

b)

Bias

c)

Input variable

d)

Transfer function

5.

Which formula correctly represents net input (n) for a neuron with a single input?

a)

n = w - b

b)

n = w + b

c)

n = wp + b

d)

n = p - b

6.

What happens to input data in the hidden layer?

a)

It's ignored

b)

It's passed directly to the output

c)

It's multiplied by weights and added to biases

d)

It's stored as memory

7.

Which of the following statements about neurons with multiple inputs is TRUE?

a)

They must have equal weights

b)

They always produce binary outputs

c)

Their net input is calculated using vector multiplication

d)

They can't be used in ANN

8.

Which transfer function produces only binary output (0 or 1)?

a)

Linear

b)

ReLU

c)

Hard-limiter

d)

Tanh

9.

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

a)

Tanh

b)

ReLU

c)

Sigmoid

d)

Linear

10.

Which activation function helps prevent the vanishing gradient problem?

a)

Sigmoid

b)

Tanh

c)

ReLU

d)

Hard-limiter

11.

What is a disadvantage of using sigmoid function in hidden layers?

a)

Not continuous

b)

Vanishing gradient problem

c)

Only works with text

d)

Cannot be differentiated

12.

What is the range of output for the tanh activation function?

a)

0 to 1

b)

-1 to 1

c)

-∞ to ∞

d)

0 to ∞

13.

Which function is most suitable for output layer in binary classification tasks?

a)

ReLU

b)

Tanh

c)

Sigmoid

d)

Linear

14.

Which layer typically shares the same transfer function in an ANN?

a)

Input layer

b)

Hidden layers

c)

Output layer

d)

All layers

15.

What is the main reason ReLU is preferred in hidden layers over sigmoid?

a)

Simpler code

b)

Better output precision

c)

Less vanishing gradient issue

d)

Better binary prediction

16.

An MLP network must contain at least:

a)

One input and one output layer only

b)

One hidden layer only

c)

One input, one hidden, and one output layer

d)

Only two layers

17.

MLP uses which type of learning method?

a)

Unsupervised

b)

Reinforcement

c)

Supervised

d)

Evolutionary

18.

Which transfer functions are commonly used in hidden layers of MLP?

a)

ReLU, Sigmoid, Tanh

b)

Linear only

c)

Hard-limiter and Linear

d)

Linear and Tanh only

19.

Which activation function is not used in hidden layers in modern MLP?

a)

ReLU

b)

Sigmoid

c)

Tanh

d)

Hard-limiter

20.

Which line of Python code adds an output layer with linear activation in Keras?

a)

model.add(Dense(1, activation='relu'))

b)

model.add(Dense(1, activation='sigmoid'))

c)

model.add(Dense(1, activation='linear'))

d)

model.add(Dense(1, activation='tanh'))