1.

The ability to regulate, measure, and understand numerical symbols, abstraction and logic is
known as ________
a. Linguistic Intelligence
b. Spatial Visual Intelligence
c. Kinaesthetic Intelligence
d. Mathematical Logical Reasoning
2. ________ refers to language processing skills both in terms of understanding or
implementation in writing or verbally. (Ans. Linguistic Intelligence)
3. Which of the following can be defined as the ability to perceive the visual world and the
relationship of one object to another?
a. Linguistic Intelligence
b. Spatial Visual Intelligence
c. Kinaesthetic Intelligence
d. Mathematical Logical Reasoning
4. If a person is well aware of self weakness and strengths or own feelings is known as
_________ intelligence. (Ans. Intrapersonal)
5. The ability to communicate with others by understanding other people’s feelings influence
the person is known as __________ intelligence.
1. Naturalist Intelligence
2. Interpersonal intelligence
3. Intrapersonal Intelligence
4. Musical Intelligence
6. The basis of decision-making depends upon
1. The available information and experience
2. Prejudices and Suggestions
3. Own beliefs and Knowledge
4. Internet facts
7. he machine’s ability to mimic human traits such as making decisions, predicting the future,
learning and improving is known as ______________.
1. Machine Intelligence
2. Artificial Intelligence
3. Machine Learning
4. Machine Automation
8. Which of the following is not a virtual assistant?
1. Alexa 2. Cortana 3. Siri 4. Chatbot
9. You are getting Amazon, Netflix, Spotify, and youtube recommendations based on which of
the following?
1. Company Rules 2. Government Policy 3. User behaviour 4. None of these
10. Which of the following is the very first humanoid robot?
1. Sophia 2. ASIMO 3. Pepper 4. Romeo
11. Which of the following is not AI?
1. Humanoid robots
2. Self Driving Cars
3. An automated Air Conditioner
4. All of these
12. ___________ is a subset of Artificial Intelligence which enables machines to improve at tasks
with experience (data). (Ans. Machine Learning)
13. Which of the following is not a domain of AI?
1. Data Science
2. Computer Vision
3. Natural Language Processing
4. Neural Network
14. ________ 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.
(Ans. Data Science)
15. Which of the following is an example of data science?
1. Social media websites
2. Price Comparison websites
3. Online Shopping websites
4. Blog web sites
16. CV stands for _____________. (Ans. Computer Vision)
17. The ________ is the domain of AI that depicts the capability of a machine to get and analyse
visual information and afterwards predict some decisions about it. (Ans. Computer
Vision/CV)
18. Which of the following is an example of a CV?
1. Self-driving cars
2. Smart Interactions
3. Face Locks
4. All of these
19. NLP stands for ___________________. (Ans. Natural Language Processing)
20. _________ is a branch of artificial intelligence that deals with the interaction between
computers and humans using the natural language. (Ans. Natural Language Processing/NLP)
21. Which of the following is an example of NLP?
1. Online translators
2. Email filters
3. Smart Assistants
4. All of these
22. Which of the following component of NLP establish linkage with natural language inputs and
analyse different aspects of language?
1. NLU
2. NLG
3. NLTK
4. NLC
23. The full form of NLU is _____________
1. Natural Language Understanding
2. Natural Language Utilization
3. Natural Language Unity
4. Natural Language Union
24. The full form of NLG is ___________
1. Natural Language Group
2. Natural Language Gap
3. Natural Language Generation
4. Natural Language gaming
25. ____________ can be defined as the science of moral duty and ideal human behaviour that
teaches what is right and what is wrong. (Ans. Ethics)
26. ________ refers to the basic principles of AI system design that use a good code of conduct
and produce the results. (Ans. AI Ethics)
27. Amazon had been working on a secret AI recruiting tool. The machine-learning specialists
uncovered a big problem: their new recruiting engine did not like women. The system taught
itself that male candidates were preferable. It penalized resumes that included the word
“women”. This led to the failure of the tool. This is an example of
1. Data Privacy
2. AI access
3. AI Bias
4. Data Exploration
28. The situation that is created by a system itself and the developer of the system cannot
resolve them is known as __________. (Ans. Black Box problem)
29. Amazon used a system for recruitment, created a situation in which many eligible females
were left out of the consideration. This is called _________.
 1. Misinterpretation of Data
2. Problem of Inclusion
3. Gender Bias
4. Data Privacy
30. Which of the following chatbot launched by Microsoft as an experimental Twitter chatbot?
1. Twitterbot
2. TwiChatBot
3. Tay
4. TwitterRobo
31. Problem scoping helps in
1. setting the goal
2. identifying the problem
3. a deeper understanding of the problem
4. All of these
32. Which of the following W of 4Ws canvas problems helps in analyzing the affected people
directly or indirectly?
1. who
2. what
3. where
4. why
33. Which of the following refers to where among 4Ws canvas?
1. stakeholders
2. nature of the problem
3. context/situation/location
4. solution or benefits to the stakeholders
34. Which of the can be a piece of information or facts and statistics collected together for
reference or analysis?
1. Data
2. Problem statement
3. Feedback
4. All of these
35. Which of the following is not a method to collect data?
1. Surveys
2. Web Scrapping
3. Sensors
4. Archives
36. Which of the following is one of the government open source for collecting data?
 1. www.ayushmanbharat.org
2. www.india.gov.in
3. www.bharatdata.in
4. www.india.com
37. Which of the following not an approach considered for modelling:
1. rule-based approach
2. learning-based approach
3. knowledge-based approach
4. All of these
38. The actual processing occurs in which of the following layer?
1. input layers
2. hidden layers
3. output layers
4. None of these
39. In which of the following type of learning networks are trained to provide the correct output
using several example units?
1. Supervised learning
2. Unsupervised learning
3. Reinforcement learning
4. All of these
40. What is an example of text classification?
Ans. Spam Filtering in email, Auto tagging customer queries, understanding audience
response from social media, categorization of news articles on specific topics.
41. Observe the graphs carefully and classify them according to how well the model’s output
matches the data samples:

Figure 1: the model’s performance matches well with the true function which states that
the model has optimum accuracy and the model is called a perfect fit.
Figure 2: The model’s output does not match the true function at all. Hence the model is
said to be underfitting and its accuracy is lower.
Figure 3: model performance is trying to cover all the data samples even if they are out of
alignment to the true function. This model is said to be overfitting and this too has lower
accuracy.
42. Define: Evaluation
 Ans.: Evaluation is the process of understanding the reliability of any AI model, based on
outputs by feeding the test dataset into the model and comparing it with actual answers.
43. Name two parameters considered for the evaluation of a model.
The two parameters considered for evaluation of a model are:
1. Prediction
2. Reality
44. What is not recommended to evaluate the model?
Its not recommended to use the data used to build the model to evaluate the model.
45. Define overfitting.
The model simply remember the whole training data set and will always predict the correct
label for any point in the training set. This is known as overfitting.
46. Enlist the data sets used in AI modelling.
There are two types of datasets used in AI.
1. Training Data Set
2. Testing Data Set
47. What do you mean by prediction?
Prediction refers to the output produced by the AI model.
48. What is reality?
Reality refers to the real scenario, when the prediction has been made by a model.
49. What are the cases considered for evaluation?
Ans.:
1. True Positive
2. True Negative
3. False Positive
4. False Negative
50. Ritika is learning evaluation. She wants to recognize the concept of evaluation from the
below-given facts:
1. A comparison between prediction and reality
2. Helps users to understand the prediction result
3. It is not an evaluation of matric
4. A record that helps in the evaluation
Help Ritika by giving the name to recognize the concept of evaluation.
Ans.: The concept is Confusion Matrix
51. What is the need for a confusion matrix?
Ans : The confusion matrix allows to understand the prediction results by an AI model.
52. What is the importance of evaluation?
 Evaluation is required to examine a model critically. It make the judgements about a model
to improve effectiveness and/or to inform programming decisions. It ensures that the model
is working properly and optionally. It helps to regulate what works well and what could be
better in a program. It is an initiative to appreciate how well it attains its goals.
53. In which situation evaluation metric is more important for any case?
Ans.: F1 evaluation metric is more significant in any case. F1 score sort of upholds a balance
between is high again F1 score is high. The F1 score is a number between 0 and 1 and is the
harmonic mean of precision and recall. The formula to determine F1 score is:
F1 Score = 2 x ( Precision x Recall) / (Precision + Recall)
54. Which value for the F1 score is the perfect F1 score? Explain with context.
Ans. When both precision and recall had the value of 1 or 100% then the F1 score is also 1 or
100%. It is known as the perfect value for F1 score. The values for precision and recall falls
between 0 and 1 likely the F1 score values also falls between 0 and 1.
55. Explain the evaluation metrics for mail spamming.
Ans.: In mail spamming, if the machine predicts that any email is spam email, then the
person will ignore that email. In this context sometime the person miss out the vital
information. False positive condition would have high cost as predicting the email as spam
while the mail is not a spam email.
56. What do you mean by Natural Processing? What is the main aim of NLP?
Ans.: Natural Language Processing or NLP is one of the sub-fields of AI that is focused on
enabling computers to understand and process human languages.
The main aim of NLP is for computers to achieve human-like comprehensions of text input.
57. Pratik is working on a huge amount of data that is full of information. Now he wants to
access a specific, important piece of information from it. Explain which NLP application
helps him.
Ans. Automatic Summarization will help to Pratik to complete his task. It is not only for
summarizing the meaning of documents and information, but also to understand the
emotional meanings within the information. For example collecting data from social media.
Automatic Summarization is specially relevant when used to provide an overview of a news
item or blog post, while avoiding redundancy from multiple sources and maximizing the
diversity of content obtained.
58. How does sentiment analysis help companies to understand what customer thinks about
their product?
Ans.: The goal of sentiment analysis is to identify the response from several posts or even in
same post where emotion is not always explicitly expressed.
 It helps to understand customer’s emotions and opinions online about their products and
services. For example, “I love new model, but sometimes it didn’t respond well and stuck in
between”.
So by this the decision makers can understand about their product reputation and
understand the reason behind or try to find it and help them to improve the mode.
59. What do you mean by syntax? Explain in detail.
The grammatical structure of a sentence. The grammatical structure contain nouns, verbs,
adverbs, adjectives, and some rules to prepare a structure. Another part of grammatical
structure is part of speech.
60. Explain with an example:
1. Perfect Syntax, no meaning
2. Multiple meanings of a word
Ans.
1. Perfect Syntax, no meaning – The sentence which is grammatically correct but it does
not make any sense. In human language, a perfect balance of syntax and semantics is
important for better understanding. Human is communication is complex. For example,
Chcikens feed extravagantly while the moon drinks tea.

2. Multiple meaning of a word – In Natural language it is important to understand that a

word can have multiple meanings and the meanings fit into the sentence according to the
context of it. For example:
1. His face turned red after he found out that he took the wrong bag.
2. The red car zoomed past his nose.
3. His face turns red after consuming the medicine
61. Explain different syntax, same semantics with example.
Ans. There are some statements which are written differently but their meanings are same.
These types of statements are known as different syntax, same semantics.
For example, 3 + 4 = 4 + 3.
In this example left side and right side both statements are written differently but semantics
are same. They will return the same output.
62. “Under tokenisation, every word, number and special character is considered separately
and each of them is now separate token”. Is this statement is correct? Explain.
Ans.: Tokens refers to any word, or number or special character occurring in a sentence.
Therefore every word, number and special character is considered separately in
tokenisation.
Example:
Tokens are the building blocks of Natural Language. Tokenization is a way of separating a
 piece of text into smaller units called tokens. Here, tokens can be either words, characters,
or subwords.
There are 38 tokens in the above sentences.
63. What is stemming? What is the purpose of stemming?
Stemming refers to the process of converting corpus into the base form of words after
removing the affixes or suffixes. In stemming the extracted words cannot be meaningful. It
just removes the affixes from the words. Stemming does not take into account if the
stemmed word is meaningful or not. It is faster in the process.
64. Write affixes and stemmed words for the following words:
controlled, controlling, controller, buddies, hobbies, thoughtful, meaningful, powerful
Ans.:
controlled : Affix – ed, Stemmed word – controll
controlling: Affix – ing, Stemmed word – controll
controller: Affix – er, stemmed word – controll
buddies: Affix – es, stemmed word – buddi
hobbies: Affix – es, stemmed word – hobbi
thoughtful : Affix – ful, stemmed word – thought
meaningful : Affix – ful, stemmed word – meaning
powerful: Affix – ful, stemmed word – power
65. What do you mean by lemmatization?
Ans. In lemmatization, the user will get the word after removal of affixes. The words which
is extracted from the original word is known as lemma. This process is little bit slow as it
will find the word with a proper meaning. Its execution is little bit slow compared to
stemming.
For example,
hobbies: affix – es, lemma – hobby
66. Explain the bag of words algorithm implementation as step by step process.
Ans.: The bag of words algorithm implemented through these steps:
1. Text Normalization: In this step, all data will be collected. After collecting the data it will
be separated by words like tokenization.
2. Create Dictionary: In this step, all the words will be written in as it is. All the words
occurring in the all documents will be written. The repeated words are written just once.
3. Create Document Vectors: Put all the words on the top as a header of table and write the
frequency of each word.
4. Create Document vectors for all documents: Do the same for all documents.
67. Create document vector for given corpus.
Document 1: We are going to play cricket.
 Document 2: We love cricket.
Document 3: We are playing cricket of 20 overs for each inning.
Document 4: We are playing cricket every Sunday.
68. Differentiate between scriptbot and smartbot.
Ans.
Scriptbot:
1. They are easy to make
2. Work through the program or script
3. It has limited functionality
4. They are less powerful
Smartbot:
1. They are difficult to make
2. Work on big databases and other resources directly
3. It has wide functionality
4. They more powerful