wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

AI Revision

Total questions: 50

Worksheet time: 50mins

Name
Class
Date
1.

From the shown diagram, which analogy is correct?

a)

Soma --> Input

b)

Axon --> Input

c)

Dendrite --> Input

d)

Synapse --> Input

2.

Which statement is correct?

a)

Output

layer: the layer that makes a prediction

b)

Input

layer: take input from another layer and pass output

to another layer

c)

Hidden

layers: directly connect to input data or produce outputs

d)

Input

layer: has highest neuron than other layer

3.

Which transfer function is always used in ANNs (Artificial Neural Networks)?
i. hard-limiter

ii. trigonometry

iii. polynomial

iv. sigmoid

a)

All above

b)

i, ii and iv

c)

i, ii and iii

d)

i and iv

4.

What type of transfer function is shown?

a)

Linear

b)

Hard-limiter

c)

Sigmoid

d)

Hyperbolic Tangent

5.

Which statement is correct?

a)

ALL

HIDDEN LAYERS typically use the different transfer function

b)

The

transfer functions that can be used for HIDDEN LAYERS is polynomial

c)

Selection

of transfer function in the HIDDEN LAYER will control how

well the neural network learns the training data

d)

The HIDDEN LAYERS should use only linear activation function

6.

What is the purpose of input data during the TESTING phase of an Artificial Neural Network (ANN)?

a)

To fine-tune the ANN's weight and bias values.

b)

To produce the predicted output during ANN simulation.

c)

To verify the initial settings of the ANN.

d)

To ensure that the ANN training data is reused for testing.

7.

How is the success of testing an artificial neural network typically determined?

a)

Testing is considered successful if the network's error rate is close to 0.

b)

Testing is said to be successful if the network's output closely matches the target values.

c)

Testing is successful if the correlation coefficient (r) is close to 1.

d)

Testing is deemed successful if the network has a large number of hidden layers.

8.

_________ type of model, the algorithm learns from a dataset which is labelled, and the algorithm uses the answer keys to evaluate its accuracy on the training data.

a)

Supervised learning

b)

Unsupervised learning

c)

Reinforcement learning

9.

In this type of model, the algorithms work towards accomplishing the goal or try to improve the performance in a particular task. This is used in gaming.

a)

Reinforcement learning

b)

Supervised Learning

c)

Unsupervised Learning

10.

•In this type of model, the algorithm learns and makes sense by extracting features/patterns from the unlabelled dataset provided (The system will evaluate by itself)

a)

Unsupervised learning

b)

supervised learning

c)

Reinforcement learning

11.

Information flows from

Input layer -> Hidden Layer-> Output layer

a)

Feedforward Network

b)

Backpropagation

12.

Every Artificial Neural must have at least ______

a)

two layers.

b)

three layers.

c)

four layers.

13.

The neurons in the human brain regularly change their threshold.

a)

True

b)

False

14.

The current Artificial Neural Networks are part of _____.

a)

Weak Al systems.

b)

Strong Al systems.

c)

Future Al systems.

15.

How many output layers are required for constructing an Artificial Neural Network?

a)

1

b)

3

c)

2

16.

The most suitable activation function for hidden layer

a)

Sigmoid

b)

ReLu

c)

Softmax

d)

tanh

17.

The number of batches needed to complete one epoch

a)

Iterations

b)

Epochs

c)

Batch

18.

When an ENTIRE dataset is passed forward and backward through the neural network only ONCE

a)

One epoch

b)

One batch

c)

One iteration

19.

How many hidden layers have the following Neural network

a)

4

b)

5

c)

6

d)

7

20.

How many input layers have the following Neural network

a)

1

b)

2

c)

3

d)

4

21.

What is a cost function?

a)

function describes how computationally expensive is a neural network

b)

an algorithm used to find the minimum of a function

c)

different name for activation function

d)

a way to determine how well the machine learning model has performed given the different values of each parameter

22.

How many output layers have the following Neural network?

a)

1

b)

2

c)

3

d)

4

23.

What is activation function?

a)

a way to determine how well the machine learning model has performed given the different values of each parameter

b)

an optimization algorithm used to find the values of parameters (coefficients) of a function (f) that minimizes a cost function (cost)

c)

function describes how computationally expensive is a neural network

d)

function used to enable Neural Network to solve non-linear problems

24.

What if the learning rate is too high?

a)

Model is difficult to converge

b)

Model consumes more computational resources

c)

Model takes longer time to converge

d)

Model is difficult to generalize

25.

__________________________ is a branch of machine learning that uses data, loads and loads of data, to teach computers how to do things only humans were capable of before.

a)

Supervised Learning

b)

Deep Learning

c)

Unsupervised Learning

26.

What is the purpose of Computer Vision?

a)

Trains computers to understand human language

b)

Trains computers to identify objects visually like a human

c)

Trains computers as a substitute for human eyes

d)

Trains computers to understand human emotion

27.

Which of the following is NOT the possible applications of Computer Vision?

a)

Detect the edges of an object

b)

Interpret typed or handwritten text

c)

Identify the sentiment of a sentence

d)

Facial recognition

28.

The first step in the Computer Vision process involves acquiring an image. Which of the following is NOT the possible source of images?

a)

Human eyes

b)

Videos

c)

Photos

d)

3D Technology

29.

The second step in the Computer Vision process involves processing the images and train the model. Which of the following tasks is NOT part of this step?

a)

Convert the images to a suitable representation

b)

Evaluate the model's accuracy

c)

Select the suitable Deep Learning algorithm

d)

Fit the model with relevant images and their labels

30.

The third step of Computer Vision involves testing whether the trained model is able to identify the objects. Why is this step important?

a)

To ensure the model is able to run

b)

To ensure the model is able to identify the objects

c)

To allow the model to learn about the objects

d)

To ensure the model is able to identify the objects accurately

31.

3. The input and output of image processing are?

a)

Signal and Image

b)

Signal Only

c)

Image Only

d)

Neither Image nor signal

32.

4. Which of the following is an Applications of Computer Vision?

a)

Robotics

b)

Medicine

c)

Security

d)

Industrial Automation

33.

6. Pixel is an _________.

a)

element of analog image

b)

element of digital image

c)

cluster of analog image

d)

cluster of digital image

34.

9. The quality of an image is dependent on ___________.

a)

Resolution of the screen

b)

Quality of Camera with which image was captured

c)

Color Depth

d)

Interlacing

35.

10. In mean filter, the value of the current pixel is replaced with

a)

mean value of pixels of the image

b)

mean value of neighbours

c)

mean value of the neighbours and current pixel

d)

None of the above

36.

system that mimic the expertise of an expert is known as

a)

Information System

b)

Computer System

c)

Expert System

d)

Super System

37.

All Information systems are Expert system but no expert system is information system

a)

True

b)

False

38.

Parts of expert system

a)

Knowledge Base

b)

Inference Engine

c)

Rule base

d)

Database

e)

Website

39.
The ability to make informed guesses from a set of facts about the subject is known as a 
a)
Theory base
b)
Knowledge base
40.

What is an advantages of an expert system?

a)

its very expensive to use

b)

errors in the rule base can lead to incorrect decisions being made

c)

it very quick and efficient to use

d)

its more accurate the real thing

41.
The ability to make decisions is based on a 
a)
Inference engine
b)
Decision machine
42.

What is a disadvantage of expert systems

a)

Expert systems require too much computing power for most modern computers to output causing the operating system to crash.

b)

Expert systems use a different kernel than standard application software which can cause errors

c)

They cannot automatically adapt to changing environments so the knowledge base has to be changed.

d)

Some Expert systems incorrectly prioritize information based on the primary key causing innacuaracy.

43.

What does the interface engine do?

a)

the 'brain' of the system, it uses the Knowledge base and the rules base and links them with the answers from the user interface to come up with a solution or to find a completely new solution

b)

the 'heart' of the system, it uses the Knowledge base and the rules base and links them with the answers from the user interface to come up with a solution or to find a completely new solution

c)

to use the Knowledge base and the Rules base to come up with answers

44.

The Step The Kernel takes in Convolution process is

a)

Padding

b)

Strides

c)

Learning Rate

45.

The Added Black Contour to the image is called

a)

Padding

b)

Filter

c)

Convolution

46.

Layer that transforms 2D Matrices to 1D Matrix

a)

Flatten Layer

b)

Convolution Layer

c)

Pooling Layer

47.

Padding and Strides can affect the

a)

Convolved Image Size

b)

Input Image Size

c)

Filter Size

48.

The main application of convolutional neural networks is?

a)

Image recognition

b)

Finding local maximum

c)

weather predictions

d)

Image classification

49.

Convolution layer is...

a)

applying a filter to an input

b)

merging similar pixels

c)

using SoftMax function on an input

d)

flattening the image

50.

Pooling layer is...

a)

applying a filter to an input

b)

merging similar pixels

c)

using SoftMax function on an input

d)

flattening the image