wayground logo

Free Printable Worksheets

Font size

S
M
L
XL
Worksheets

Neural & Big data

Total questions: 92

Worksheet time: 55mins

Name
Class
Date
1.

_________ 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

2.

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

3.

•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

4.

Information flows from

Input layer -> Hidden Layer-> Output layer

a)

Feedforward Network

b)

Backpropagation

5.

Every Artificial Neural must have at least ______

a)

two layers.

b)

three layers.

c)

four layers.

6.

The neurons in the human brain regularly change their threshold.

a)

True

b)

False

7.

The current Artificial Neural Networks are part of _____.

a)

Weak Al systems.

b)

Strong Al systems.

c)

Future Al systems.

8.

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

a)

1

b)

3

c)

2

9.

Conventional Computing is deterministic in nature while Neural Computing is Probabilistic in nature.

a)

True

b)

False

10.

Backpropagation calculates the ____ and propagates it back to earlier layers.

a)

value

b)

error

c)

data

11.

Neural network is inspired by .......

a)

Human heart

b)

Human lungs

c)

Human brain

d)

human eyes

12.

Neural Network is type of ........... which is type of machine learning

a)

natural language processing

b)

deep learning

c)

speech

d)

robotics

13.

What is this?

a)

artificial intelligence

b)

algorithm

c)

neural network

14.

How many hidden layers have the following Neural network

a)

4

b)

5

c)

6

d)

7

15.

The most common Neural networks consist of three network layers: input layer, output layer and .............

a)

neuron layer

b)

hidden layer

c)

algorithm layer

16.

The input data travels over the network (propagates) until it reaches the output layer. This is called........

a)

Back propagation

b)

Forward propagation

17.

This is where we insert the initial data for the neural network.

a)

Input

b)

Hidden Layer

c)

Output

18.

_________ 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

19.

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

20.

•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

21.

Every Artificial Neural must have at least ______

a)

two layers.

b)

three layers.

c)

four layers.

22.

The current Artificial Neural Networks are part of _____.

a)

Weak Al systems.

b)

Strong Al systems.

c)

Future Al systems.

23.

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

a)

1

b)

3

c)

2

24.

A neural network trained with labelled data is an example of . . .

a)

supervised learning

b)

unsupervised learning

25.

In the neural network shown,

a)

each neuron is connected to a random selection of other neurons in the network

b)

every neuron is connected to every other neuron in the network

c)

every neuron is conected to every neuron in the next layer

d)

each neuron is connected to a random selection of neurons in the next layer

26.

The activation of each neuron in a layer is determined by the __________ of the activations of all the neurons in the previous layer.

a)

weighted sum

b)

sum

c)

level

27.

How many hidden layers have the following Neural network

a)

4

b)

5

c)

6

d)

7

28.

How many output layers have the following Neural network?

a)

1

b)

2

c)

3

d)

4

29.

The most common Neural networks consist of three network layers: input layer, output layer and .............

a)

neuron layer

b)

hidden layer

c)

algorithm layer

30.

Which of the following is the feature of a neural network?

a)

Extract information without any programming

b)

All of these

c)

Learn itself and produced the trained data

d)

Provide the filtered information without input

31.

The actual processing occurs in which of the following layer?

a)

input layers

b)

hidden layers

c)

output layers

d)

None of these

32.

Reinforcement learning relies on output-related information.

a)

True

b)

False

33.

In _________ learning only inputs provided but no output related data.

a)

Supervised

b)

Reinforcement

c)

Un supervised

d)

Semi-Supervised

34.
What are the Three Parts of a Neuron?
a)
Dendrite, Saxon, Aoma
b)
Gamio, Saxio, Dendrition
c)
Dendrite, Soma, Axon
d)
Dęndrìtē, Âxòn, Sómä
35.
What Problems do ANNs not solve?
a)
Geometric problems
b)
Science problems
c)
Industry problems
d)
Financial problems
36.
What futuristic actions can not be performed by ANNs?
a)
Pattern Recognition
b)
Function Approximation
c)
Pattern Classification
d)
Facial Recognition
37.

1)    It is the ability of a digital computer or computer-controlled robot to perform tasks commonly associated with intelligent beings

a)

Automated computations

b)

IOT

c)

Artificial Intelligence

d)

None of these

38.

(a)   is a domain of AI related to data systems and processes, in which the system collects numerous data, maintains data sets and derives meaning/sense out of

them.

39.

It is a subset of Artificial Intelligence which enables machines to improve at tasks with experience (data).

a)

Machine Learning

b)

AI

c)

Deep Learning

40.

In this model, the machine is trained with huge amounts of data which helps it in training itself around the data. Such machines are intelligent enough to develop algorithms for themselves.

a)

AI

b)

ML

c)

DL

41.

Domain of the game Rock Paper Scissors is

a)

NLP

b)

Data Science

c)

Computer Vision

42.

Domain of the AI used by price comparison websites is

a)

Data Science

b)

NLP

c)

CV

43.

The __________ helps us to summarise all the key points of Problem Scoping.

a)

Problem Statement Template

b)

4 Ws Problem canvas

c)

Data Features

44.

Identify the correct order of the 4Ws problem canvas.

a)

Who? Why? When? Where?

b)

Who? What? Where? Why?

c)

Why? What? Where Who?

d)

Why? What? Who? Where?

45.

Under this block, you also gather evidence to prove that the problem you have selected actually exists. Identify the block of 4W problem canvas.

a)

Who

b)

what

c)

where

d)

why

46.

The AI domain which can be used to predict AIR quality index is

a)

NLP

b)

CV

c)

Data Science

47.

Which of the following is not an AI application?

a)

Google Maps

b)

Writing suggestion in gmail

c)

Face Recognition

d)

Kahoot

48.

4Ws Problem Canvas _______________________.

a)

make many lives better and help our country achieve these goals.

b)

helps in evaluating the solution related to the problem

c)

helps in identifying the key elements related to the problem.

d)

All of these

49.

computational model inspired by the structure and functions of the biological neural network

a)

artificial neural network (ANN)

b)

neuron

c)

weight

d)

bias

50.

collection of 'neurons' operating together at a specific depth within a neural network

a)

Bias

b)

Weight

c)

Neuron

d)

Layers

51.

How many images would you need of a cat, for example, to train a neural network ?

a)

about 10

b)

a few hundred

c)

one image

d)

thousands

52.
What are ANNs used for?
a)
Reproduce Human Spinal Functions
b)
Reproduce Human Foot Functions
c)
Reproduce Human Nervous System
d)
Reproduce Human Brain Functions
53.
What two types of Neural Networks are there
a)
Biological Neural network and Artificial Neural Network
b)
Chemical Neural Network and Biological Neural Network
c)
Geological Neural Network and Artificial Neural Network
d)
Chemical Neural Network and Geological Neural Network
54.

Which is the correct structure of a Neural Network?

a)

Output, Hidden Layer, Input

b)

Hidden Layer, Input, Output

c)

Input, Hidden Layer, Output

55.

Which one of these is not an area of AI?

a)

computer vision/image recognition

b)

voice recognition

c)

web design

d)

robotics

56.

This is a system of Programs and Data Structures that mimics the operation of the human brain :

a)

Intelligent Network

b)

Decision Support System

c)

Neural Network

d)

Genetic Programming

57.

Which of the following is a common application of AI in everyday life?

a)

Sending emails

b)

Autonomous vehicles

c)

Printing documents

d)

Automated lawn mowers

58.

What is the primary goal of artificial intelligence?

a)

To replace human workers entirely

b)

To simulate human intelligence and perform tasks that typically require human intelligence

c)

To enhance the emotional capabilities of machines

d)

To process large amounts of data quickly and accurately

59.

What is big data analytics?

a)

D. The process of analyzing data for entertainment purposes

b)

C. The process of analyzing only structured data

c)

B. The process of examining big data to uncover information

d)

A. The process of examining small data sets

60.

Why is big data analytics important?

a)

B. To increase the amount of unstructured data

b)

C. To complicate decision-making processes

c)

A. To make data-driven decisions that can improve business outcomes

d)

D. To reduce operational efficiency

61.

How does big data analytics work?

a)

A. By ignoring unstructured data

b)

B. By analyzing only historical data

c)

C. By collecting, processing, cleaning, and analyzing data

d)

D. By focusing on basic business intelligence queries

62.

What are some benefits of using big data analytics?

a)

D. Improved decision-making, talent shortages, and data accessibility

b)

C. Cost savings, improved decision-making, and real-time intelligence

c)

B. Better customer engagement, optimize risk management strategies, and talent shortages

d)

A. Real-time intelligence, better-informed decisions, and cost increases

63.

What is the primary goal of predictive analytics in big data?

a)

A. To analyze historical data for insights

b)

B. To forecast future trends and outcomes

c)

C. To organize unstructured data efficiently

d)

D. To focus on real-time data processing

64.

What role does machine learning play in big data analytics?

a)

A. Machine learning is not relevant in big data analytics

b)

B. Machine learning helps in automating data analysis tasks

c)

C. Machine learning is only used for data storage in big data analytics

d)

D. Machine learning is limited to basic statistical analysis in big data

65.

What is associated with the three words :velocity, volume and variety

a)

Large Files

b)

Databases

c)

Big Data

d)

Huge Data

66.

Which of the traditional IT systems presents better analytical options when used with Big Data technologies

a)

conventional data

b)

conventional databases

c)

Data warehouses

d)

None of the above

67.

________ is the process of examining very large and varied data sets.

a)

Machine Learning

b)

Data warehousing

c)

Big Data Analytics

d)

Cloud Computing

68.

Point out the wrong statement.

a)

Hardtop processing capabilities are huge and it’s real advantage lies in the ability to process terabytes & petabytes of data

b)

All the programs should confirms to HDFS model in order to work on Hadoop platform

c)

The programming model used by HDFS is difficult to write and test.

d)

All of the mentioned

69.

The characteristics of big data includes __________.

a)

composition

b)

condition

c)

context

d)

All of the above

70.

_____________ deals with the nature of the data as it is static or varied with time.

a)

composition

b)

condition

c)

context

d)

none of the above

71.

Which of the characteristic(s) of big data is relatively more concerned to data science?

a)

Velocity

b)

Variety

c)

Volume

d)

All of the above

72.

Select the wrong statement from the following list of statements:

a)

The big volume indeed represents Big Data

b)

The data growth and social media explosion have changed how we look at the data

c)

Big Data is just about lots of data

d)

All of the mentioned

73.

Comment on the statement: 3V’s are not sufficient to describe big data.

a)

True

b)

False

74.

Which of the language(s) are used to do Big Data Analytics

a)

C

b)

Python

c)

Java

d)

R

e)

SQL

75.

Data Veracity means _______________________.

a)

imprecise data

b)

uncertain data

c)

variety of data

d)

different sources of data

76.

_____________ tells about where the data has been generated.

a)

composition

b)

context

c)

condition

d)

class

77.

Which of the following statement(s) is/are true?

a)

Descriptive analysis can be more useful for defining future studies

b)

Correlation does imply causation

c)

Inference is commonly the goal of statistical model

d)

None of the mentioned

78.

What is Big Data?

a)

Big Data is a type of software used for data storage.

b)

Big Data refers to small data sets that are easy to analyze.

c)

Big Data is only relevant to social media platforms.

d)

Big Data is large and complex data sets that require advanced tools and techniques for processing and analysis.

79.

Name three key technologies used in Big Data.

a)

Excel, PowerPoint, Word

b)

Hadoop, Spark, NoSQL databases

c)

MySQL, PostgreSQL, Oracle

d)

Java, Python, C++

80.

What is the purpose of predictive analytics?

a)

To collect data without any analysis.

b)

The purpose of predictive analytics is to forecast future events and trends based on historical data.

c)

To analyze current market conditions only.

d)

To eliminate the need for data altogether.

81.

Describe one method of predictive analytics.

a)

Decision trees

b)

Cluster analysis

c)

Regression analysis

d)

Time series analysis

82.

What is the difference between data analytics and data analysis?

a)

Data analysis is a broader term encompassing various techniques.

b)

Data analytics and data analysis are interchangeable terms.

c)

Data analytics is a specific process within data analysis.

d)

Data analytics is a broader term encompassing various techniques, while data analysis is a specific process within data analytics.

83.

List two common tools used for data analysis.

a)

Tableau

b)

Microsoft Excel, Python

c)

R

d)

Google Docs

84.

What role does machine learning play in predictive analytics?

a)

Predictive analytics does not involve any data analysis techniques.

b)

Machine learning is only used for image recognition tasks.

c)

Machine learning is primarily focused on hardware improvements.

d)

Machine learning enhances predictive analytics by identifying patterns in data to forecast future events.

85.

Explain the concept of network analysis.

a)

Network analysis is the study of relationships and interactions within a network using nodes and edges.

b)

Network analysis focuses solely on the speed of data transmission.

c)

Network analysis is the process of creating physical network hardware.

d)

Network analysis is a method for designing software applications.

86.

How is network analysis applied in computational social science?

a)

Network analysis focuses solely on the physical infrastructure of the internet.

b)

Network analysis is used to study relationships and interactions in social networks, revealing patterns and influences among individuals or groups.

c)

Network analysis is used to track financial transactions in banking systems.

d)

Network analysis is primarily concerned with the technical performance of computer networks.

87.

What are the challenges associated with Big Data technologies?

a)

Increased reliance on manual data entry

b)

Challenges include data storage, processing speed, data quality, integration, security, and skilled personnel.

c)

Limited use of cloud computing

d)

High cost of traditional storage solutions

88.

Define data mining and its significance in data analytics.

a)

Data mining is the process of discovering patterns and knowledge from large amounts of data, and it is significant in data analytics for transforming raw data into actionable insights.

b)

Data mining is only used for financial forecasting.

c)

Data mining involves only the collection of data without analysis.

d)

Data mining is the same as data entry and has no significance in analytics.

89.

What is the importance of data visualization in data analysis?

a)

Data visualization complicates data analysis.

b)

Data visualization enhances understanding, reveals insights, and improves communication in data analysis.

c)

Data visualization is only useful for large datasets.

d)

Data visualization has no impact on decision-making.

90.

How can Big Data impact decision-making processes?

a)

Big Data has no effect on decision-making as intuition is always more reliable.

b)

Big Data impacts decision-making by providing data-driven insights that improve accuracy and speed.

c)

Big Data only benefits marketing departments and does not influence other areas of decision-making.

d)

Big Data slows down decision-making processes by overwhelming teams with irrelevant information.

91.

What are some ethical considerations in data analytics?

a)

Statistical analysis methods

b)

Data privacy, informed consent, bias avoidance, data security, transparency.

c)

Data visualization techniques

d)

Machine learning algorithms

92.

Describe a real-world application of predictive analytics.

a)

Predictive analytics in finance for stock market analysis.

b)

Predictive analytics in agriculture for crop yield prediction.

c)

Predictive analytics in healthcare for forecasting patient admissions.

d)

Predictive analytics in marketing for customer segmentation.