STUDENT
ARTIFICIAL INTELLIGENCE PRACTICE TEST
Total Q: 40
Time: 40 Mins
Q 1.
Sarthak made a face mask detector system for which he had collected the dataset and used all the dataset to train the model. Then, he used some different data set to evaluate the model which resulted in the correct answer all the time. Name the concept.
Perfect Fit
Under Fitting
Over Fitting
Correct Fit
Q 2.
How many channels does a colour image have?
1
2
3
4
Q 3.
Look at the two documents:
Document 1: We can use health chatbots for treating stress.
Document 2: We can use NLP to create chatbots and we will be making health chatbots now!
Identify the term in which we can categorise the word 'Chatbots'
Stop word
Rare word
Frequent word
Removable word
Q 4.
Srishti is a young woman who makes earrings. She buys jute from a farmer and makes earrings from that. She sees that most women in her village do not work. So, she hires two women to help her. As her orders increase, she hires three more women to work for her. How was she helping her village grow?
By selling earrings to women without a job
By purchasing earrings from the local market
By buying jute from the local farmer and by providing jobs to local women
By attracting the women in her village with her creative earrings
Q 5.
Which of the following are Command Keys.
INSERT (INS) and DELETE (DEL)
A & Z
F1 & F2
0 & 1
Q 6.
The four R's of waste management are
Refuse, Reduce, Reuse, Recycle
Repair, Reduce, Reuse, Refuse
Refuse, Reduce, Recover, Recycle
Refuse, Reduce, Rethink, Recycle
Q 7.
_____ is a practice where an individual is supposed to focus his/her mind on a particular object, thought or activity to achieve a calm mental state reducing stress.
Enjoying
Meditation
Physical exercise
Going on vacations with family and friends
Q 8.
Which among the following is NOT a correct example for "Small group discussion"?
Press conferences
Election campaigns
Board meetings
Team meetings
Q 9.
An AI bot recommends surgery to a patient. The doctor still discusses all options with the patient before making a decision. Which principle is followed?
Beneficence
Non-maleficence
Justice
Autonomy
Q 10.
The process of attaching meaning or tags to data is called:
Labeling
Clustering
Associating
Grouping
Q 11.
Which of the following best defines Instance Segmentation?
Labeling entire image
Detecting single object
Detecting and labeling each pixel for each object
Identifying image size
Q 12.
When evaluating a model with a highly imbalanced dataset, which metric is generally more informative than accuracy?
Precision
Recall
F1 Score
All of the above
Q 13.
Which of the following is NOT a principle of bioethics?
Justice
Accuracy
Non-maleficence
Beneficence
Q 14.
Rule-based AI fails when:
It is trained on large datasets
The training data changes and model can't adapt
Labeled data is provided
Reinforcement signals are given
Q 15.
Which step in text normalization involves breaking down text into individual words, numbers, or symbols?
Lemmatization
Stemming
Tokenization
Sentence Segmentation
Q 16.
In NLP, what is the main function of discourse integration?
Checking grammar rules
Making sense of a sentence's meaning in isolation
Establishing context between sentences
Removing stopwords from text
Q 17.
What does a Neural Network consist of?
Only input and output layers
Fixed rules and if-else logic
Layers made up of nodes that process data
Unlabeled training data only
Q 18.
Rohan is creating an AI that reads handwritten homework and stores marks. He trains the AI using thousands of scanned papers. Which AI domain is this?
Statistical Data
Computer Vision
Natural Language Processing
Robotics
Q 19.
When would you use the F1 Score over other metrics?
When data is balanced and all predictions matter equally
When overfitting is a major issue
When you need a single measure that balances precision and recall
When only true negatives are important
Q 20.
An AI system that analyses photographs and videos belongs to which domain?
NLP
Computer Vision
Statistical Data
None of the above
Q 21.
Identify the given Chat bot type:
It learns from its environment and experience. It also builds on its capabilities based on the knowledge. These can collaborate with humans, working along-side them and learning from their behavior.
Script Bot
Smart Bot
AI Bot
Chat Bot
Q 22.
Statement 1 : Confusion matrix is an evaluation metric.
Statement 2 : Confusion Matrix is a record which helps in evaluation.
Both Statement 1 and Statement 2 are correct.
Both Statement 1 and Statement 2 are incorrect.
Statement 1 is correct and Statement 2 is incorrect.
Statement 2 is correct and Statement 1 is incorrect.
Q 23.
Aman want to make an Artificially Intelligent system which can predict the salary of any employee based on his previous salaries. He has to feed the data of his previous salaries. This is the data with which the machine can be trained. The previous salary data here is known as_______ while the next salary prediction data set is known as the ________
Testing Data, Training Data
Training Data, Testing Data
Training Data, Next Data
First Data, Testing Data
Q 24.
_________________is the sub-field of AI that is focused on enabling computers to understand and process human languages.
Deep Learning
Machine Learning
NLP
Data Sciences
Q 25.
Assertion(A) : Neural networks are the backbone of deep learning algorithms
Reason(R): Neural networks use vast amounts of data
Both A and R are correct and R is the correct explanation of A
Both A and R are correct but R is NOT the correct explanation of A
A is correct but R is not correct
A is not correct but R is correct.
Q 26.
What does a high precision value indicate in a classification model?
The model rarely misses positive cases
The model correctly identifies negative cases
The model makes very few false positive errors
The model is overfitted
Q 27.
An AI app helps farmers decide when to water crops based on weather and soil data. Which stage is most important for collecting this data?
Modeling
Data Acquisition
Deployment
Problem Scoping
Q 28.
Which stage involves integrating the AI model into the real world for usage?
Deployment
Modeling
Data Acquisition
Evaluation
Q 29.
Labeled data means:
Data that is hidden from the model
Data with predefined tags or outcomes
Data stored in images only
Data that cannot be used in AI
Q 30.
Aditi, a student of class XII developed a chatbot that clarifies the doubts of Economics students. She trained the software with lots of data sets catering to all difficulty levels. If any student would type or ask questions related to Economics, the software would give an instant reply. Identify the domain of AI in the given scenario.
Computer Vision
Data Science
Natural Language Processing
None of these
Q 31.
Which of the following is NOT a classification metric?
Accuracy
Recall
Mean Squared Error
Precision
Q 32.
Identify the type of chatbot with the information given below: These bots work on pre-programmed instructions inside the application/machine and are generally easy to develop. They are deployed in the customer care section of various companies. Their job is to answer some basic queries that they are coded for and connect them to human executives once they are unable to handle the conversation.
Script Bot
Smart Bot
AI Bot
Chat Bot
Q 33.
If Data is represented as "Answer", Processing is represented as "Data" and Answer is represented as "Processing", which of the following can be related to the description of layers in a neural network? Choose the correct options
Input Layer -> Data; Output layer -> Processing; Hidden Layer -> Answer
Input Layer -> Processing; Output layer -> Data; Hidden Layer -> Answer
Input Layer -> Answer; Output layer -> Processing; Hidden Layer -> Data
Input Layer -> Answer; Output layer ->Data; Hidden Layer -> Processing
Q 34.
An AI system that predicts student performance uses past test scores and attendance. This kind of data is part of:
NLP
Computer Vision
Statistical Data
Robotics
Q 35.
Rajat has made a model which predicts the performance of Indian Cricket players in upcoming matches. He collected the data of players' performance with respect to stadium, bowlers, opponent team and health. His model works with good accuracy and precision value. Which of the statement given below is incorrect?
Data gathered with respect to stadium, bowlers, opponent team and health is known as Testing Data.
Data given to an AI model to check accuracy and precision is Testing Data.
Training data and testing data are acquired in the Data Acquisition stage.
Training data is always larger as compared to testing data.
Q 36.
Why is it not ideal to use the training dataset to evaluate a model?
Because it reduces the model's performance
Because it introduces randomness
Because the model might overfit and remember the training data
Because it makes the model too complex
Q 37.
You are training a model to detect spam emails. What kind of data do you need to provide for training?
Unlabeled data only
A list of email IDs
Labeled data showing which emails are spam or not
Photos of inbox folders
Q 38.
What is the first stage of the AI Project Cycle?
Modeling
Deployment
Problem Scoping
Data Exploration
Q 39.
Which of the following is the first step in the stages of Natural Language Processing (NLP)?
Semantic Analysis
Lexical Analysis
Pragmatic Analysis
Discourse Integration
Q 40.
Observe the given graph and fill in the blank:
__________ the neural network, better is the performance.
Larger
Smaller
Medium
Traditional ML