Class X Part B Unit 2 AI Project Cycle

You might also like

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 16

Competency based multiple choice questions:

Question 1

Which of the following stages is the FIRST step in the AI project cycle and focuses on identifying and
understanding the problem using 4Ws (Who, What, Where, and Why)?

A. Data Acquisition B. Data Exploration C. Problem Scoping D. Modelling

Answer: C. Problem Scoping


Explanation:

The chapter states that problem scoping is the first and crucial stage of AI project development. It focuses on
identifying and understanding the problem using a 4W approach (Who, What, Where, and Why).

Question 2

Unsupervised learning is a type of machine learning approach that works on __________ data.

A. labeled B. unlabeled C. partially labeled D. all of the above

Answer: B. unlabeled
Explanation:

The chapter explains that unsupervised learning works on unlabeled datasets, meaning the data fed to the
machine is random and there is no known information available about it.

Question 3

In the context of AI project development, what is the main purpose of data visualization?

A. To create colorful charts to impress stakeholders B. To allow machines to understand the data C. To
quickly grasp trends, relationships, and patterns within the data D. To transform data into a different format
for storage purposes

Answer: C. To quickly grasp trends, relationships, and patterns within the data
Explanation:

The chapter highlights that data visualization plays a vital role in data analysis. It helps users to quickly
identify trends, relationships, and patterns within the data. This information is crucial for defining the
strategy for the type of model used in a later stage of the AI project cycle.

Question 4
Which of the following is NOT a type of machine learning model covered in the chapter?

A. Decision Tree (not mentioned in the doc) B. Support Vector Machine (not mentioned in the doc) C. Rule-
based approach D. Unsupervised learning

Answer: A. Decision Tree (not mentioned in the chapter)


Explanation:

The chapter covers rule-based approaches, unsupervised learning, and supervised learning models (including
regression) but does not mention Decision Trees.

Question 5

Neural networks are a type of deep learning algorithm inspired by the structure of the ________.

A. Human brain B. Animal nervous system C. Computer processor D. Internet network

Answer: A. Human brain


Explanation:

The chapter clarifies that neural networks are inspired by the structure of the human brain. Neural networks
are designed to learn and improve like the human brain by recognizing hidden patterns in raw data.

Competency based multiple choice questions in the pattern of assertion


reason:

Question 1

Assertion (A): Artificial intelligence (AI) is used in various applications like traffic flow prediction and
medical diagnosis. Reason (R): AI can process large amounts of data and identify patterns that humans
might miss.

Options:

1. (A) is true, (R) is true; (R) is a correct explanation of (A). ✔


2. (A) is true, (R) is false.
3. (A) is false, (R) is true.
4. (A) is false, (R) is false.
Explanation:
AI is used in various applications because it can process large amounts of data and identify patterns that
humans might miss. So, both Assertion (A) and Reason (R) are true, and Reason (R) is a correct explanation
of Assertion (A).

Question 2

Assertion (A): The stages of the AI project cycle include problem scoping, data acquisition, data
exploration, modelling, and evaluation. Reason (R): Following these stages ensures a well-defined problem
and efficient use of data.

Options:

1. (A) is true, (R) is true; (R) is a correct explanation of (A). ✔


2. (A) is true, (R) is false.
3. (A) is false, (R) is true.
4. (A) is false, (R) is false.
Explanation:

The stages of the AI project cycle help ensure a well-defined problem and efficient use of data by guiding
the process from problem identification to model evaluation. So, both Assertion (A) and Reason (R) are true,
and Reason (R) is a correct explanation of Assertion (A).

Question 3

Assertion (A): Unsupervised learning is a type of machine learning where the data is labelled.

Options:

1. (A) is true, (R) is true; (R) is a correct explanation of (A).


2. (A) is true, (R) is false. ✔
3. (A) is false, (R) is true.
4. (A) is false, (R) is false.
Explanation:

Unsupervised learning deals with unlabeled data, where the machine identifies patterns and relationships on
its own. So, Assertion (A) is false.

Question 4

Assertion (A): Neural networks are inspired by the structure and function of the human brain.

Options:
1. (A) is true, (R) is true; (R) is a correct explanation of (A). ✔
2. (A) is true, (R) is false.
3. (A) is false, (R) is true.
4. (A) is false, (R) is false.
Explanation:

Neural networks are inspired by the structure and function of the human brain, with interconnected nodes
that process information and learn from patterns. So, both Assertion (A) and Reason (R) are true, and
Reason (R) is a correct explanation of Assertion (A).

Question 5

Assertion (A): Machine learning algorithms are always accurate and reliable.

Options:

1. (A) is true, (R) is true; (R) is a correct explanation of (A).


2. (A) is true, (R) is false.
3. (A) is false, (R) is true. ✔
4. (A) is false, (R) is false.
Explanation:

Machine learning algorithms can be inaccurate and unreliable, especially with limited data or complex
problems. So, Assertion (A) is false.

Competency based multiple choice questions in the pattern of statement1


statement2:

Question 1

Statement 1: Data exploration is a crucial stage in the AI project cycle. Statement 2: Data exploration helps
identify patterns and trends in the data.

 A. Both statements are true, and statement 2 explains statement 1.


 B. Both statements are true, but statement 2 does not explain statement 1.
 C. Statement 1 is true, but statement 2 is false.
 D. Statement 1 is false, but statement 2 is true.
Explanation: The correct answer is (A). Data exploration allows us to uncover patterns that will inform the
AI model building process.
Question 2
Statement 1: A neural network is a type of machine learning model inspired by the structure of the human
brain. Statement 2: Neural networks are capable of learning and improving without being explicitly
programmed.

 A. Both statements are true, and statement 2 explains statement 1.


 B. Both statements are true, but statement 2 does not explain statement 1.
 C. Statement 1 is true, but statement 2 is false.
 D. Statement 1 is false, but statement 2 is true.
Explanation: The correct answer is (A). The structure of neural networks and their interconnected nodes
enable them to learn complex patterns from data and adapt to make improved predictions.
Question 3

Statement 1: Supervised learning is a machine learning approach where the data is labeled. Statement 2:
Supervised learning algorithms learn from labeled data to make predictions on new, unseen data.

 A. Both statements are true, and statement 2 explains statement 1.


 B. Both statements are true, but statement 2 does not explain statement 1.
 C. Statement 1 is true, but statement 2 is false.
 D. Statement 1 is false, but statement 2 is true.
Explanation: The correct answer is (A). Supervised learning thrives on labeled data, using the provided
labels to train the model for future prediction tasks.
Question 4

Statement 1: Unsupervised learning is a machine learning approach used for clustering data. Statement 2:
Unsupervised learning algorithms group data points based on similarities without any predefined labels.

 A. Both statements are true, and statement 2 explains statement 1.


 B. Both statements are true, but statement 2 does not explain statement 1.
 C. Statement 1 is true, but statement 2 is false.
 D. Statement 1 is false, but statement 2 is true.
Explanation: The correct answer is (A). Unsupervised learning helps group data based on similar traits,
without the model learning from pre-assigned labels.
Question 5

Statement 1: Evaluation is the final stage in the AI project cycle. Statement 2: The evaluation stage helps
assess the performance of the AI model.

 A. Both statements are true, and statement 2 explains statement 1.


 B. Both statements are true, but statement 2 does not explain statement 1.
 C. Statement 1 is true, but statement 2 is false.
 D. Statement 1 is false, but statement 2 is true.
Explanation: The correct answer is (A). Evaluating a model's performance on unseen data is crucial and
helps determine its effectiveness and areas for improvement.

Case study based multiple choice type questions:

Scenario 1: Automated Medical Diagnosis


Question: Dr. Li decides to trust the machine learning algorithm's diagnosis completely. What potential
risks are associated with this approach?
 A. The algorithm could be incorrect, leading to a misdiagnosis.
 B. Dr. Li could become over-reliant on the algorithm, losing critical diagnostic skills.
 C. The algorithm might not account for individual patient factors.
 D. All of the above.
Explanation: The correct answer is (D). All of the above choices present potential risks associated with
fully relying on a machine learning algorithm for diagnosis.
Question: How can machine learning be a valuable tool for radiologists like Dr. Li?
 A. It can provide a second opinion and highlight areas of interest.
 B. It can analyze large amounts of medical images quickly.
 C. It can assist in the early detection of diseases.
 D. All of the above.
Explanation: The correct answer is (D). Machine learning offers numerous benefits to radiologists in image
analysis and diagnosis.
Scenario 2: AI-powered Wildlife Conservation
Question: How can AI-powered camera traps assist park rangers like Aisha in their conservation efforts?
 A. Detect poachers entering restricted areas.
 B. Monitor animal populations and identify endangered species.
 C. Track animal movement patterns and behaviors.
 D. All of the above.
Explanation: The correct answer is (D). AI-powered camera traps have multiple applications in wildlife
conservation.
Question: What are some of the challenges associated with using AI for wildlife conservation?
 A. High costs of equipment and software.
 B. Limited data on rare or endangered species.
 C. Environmental factors (weather, terrain) affecting image quality.
 D. All of the above.
Explanation: The correct answer is (D). There are several challenges to consider when implementing AI
solutions in wildlife conservation.
Scenario 3: AI in Education
Question: What are some of the potential benefits of using AI-powered tutoring platforms in the classroom?
 A. Provide personalized learning paths for each student.
 B. Identify areas where students need extra support.
 C. Free up teachers' time to focus on individual instruction.
 D. All of the above.
Explanation: The correct answer is (D). AI-powered tutoring platforms offer various benefits in a
classroom setting.
Question: What are some of the potential drawbacks of using AI-powered tutoring platforms in the
classroom?
 A. AI tutors cannot replace the human connection and guidance of a teacher.
 B. Students might become too dependent on the technology.
 C. There are concerns about data privacy and how student information is used.
 D. All of the above.
Explanation: The correct answer is (D). It's important to consider the potential drawbacks alongside the
benefits of AI in education.

Case study based multiple choice type questions in the pattern of assertion
reason:

Scenario 1

Character: Zara, a Data Scientist at a climate research institute

Task: Zara is building a machine learning model to predict wildfires. She wants to use a supervised learning
approach.

Question 1

Assertion (A): Zara should use labeled data for training her model. Reason (R): Supervised learning models
require labeled data for training.

Options:
1. (A) is true, (R) is true; (R) is a correct explanation of (A). [Correct Answer]
2. (A) is true, (R) is true; (R) is not a correct explanation of (A).
3. (A) is false, (R) is true.
4. (A) is false, (R) is false.
Explanation:

Supervised learning models require labeled data for training, where the data is tagged with the desired
output. In this case, the labeled data for Zara's model would include historical data on wildfires, along with
factors that might influence them, such as temperature, humidity, and vegetation cover. By training the
model on this labeled data, the model can learn to identify patterns and relationships between these factors
and wildfires, allowing it to predict future wildfires with some accuracy.

Scenario 2

Character: Rohan, a farmer

Task: Rohan wants to improve the yield of his crops using AI. He doesn't have any labeled data about his
farm.

Question 2

Assertion (A): Rohan can use unsupervised learning for this task. Reason (R): Unsupervised learning models
can identify patterns in unlabeled data.

Options:
1. (A) is true, (R) is true; (R) is a correct explanation of (A). [Correct Answer]
2. (A) is true, (R) is true; (R) is not a correct explanation of (A).
3. (A) is false, (R) is true.
4. (A) is false, (R) is false.
Explanation:

Since Rohan doesn't have any labeled data about his farm, supervised learning won't be suitable. However,
unsupervised learning can be a good option in this scenario. Rohan can use an unsupervised learning model
to identify patterns in his existing data, such as sensor data on soil moisture, temperature, and crop growth.
These patterns might reveal relationships between these factors and crop yield, which Rohan can then use to
improve his farming practices.

Scenario 3

Character: A self-driving car company

Task: The company is developing a self-driving car that needs to navigate through different weather
conditions .

Question 3
Assertion (A): The company should use a neural network for this task. Reason (R): Neural networks are
good at handling complex patterns.

Options:
1. (A) is true, (R) is true; (R) is a correct explanation of (A). [Correct Answer]
2. (A) is true, (R) is true; (R) is not a correct explanation of (A).
3. (A) is false, (R) is true.
4. (A) is false, (R) is false.
Explanation:

Navigating through different weather conditions is a complex task that requires the self-driving car to
recognize and react to various patterns, such as rain, snow, fog, and sunlight. Neural networks are a type of
machine learning model that is well-suited for handling complex patterns. By training a neural network on a
large dataset of images and sensor data captured under different weather conditions, the self-driving car can
learn to identify these patterns and adjust its behavior accordingly.

Scenario 4

Character: Medical research facility

Task: They are analyzing medical images to detect cancer cells.

Question 4

Assertion (A): The facility should use convolutional neural networks (CNNs) for this task. Reason (R):
CNNs are particularly effective for image analysis.

Options:
1. (A) is true, (R) is true; (R) is a correct explanation of (A). [Correct Answer]
2. (A) is true, (R) is true; (R) is not a correct explanation of (A).
3. (A) is false, (R) is true.
4. (A) is false, (R) is false.
Explanation:

Convolutional neural networks excel at image analysis tasks due to their specialized architecture. They are
designed to process visual data and learn hierarchical representations of features within images. This makes
them ideal for detecting subtle patterns within medical images that might indicate the presence of cancer
cells.
Case study based multiple choice type questions in the pattern of statement1
statement2:

Scenario 1

Character: Aditi, a social media influencer

Task: Aditi wants to analyze the sentiment of her followers' comments on her latest video to understand their
reaction.

Statement 1: Aditi can use a rule-based approach to achieve this task.

Statement 2: Rule-based approaches require defining a set of rules to categorize the sentiment of the
comments.

Options:
1. Statement 1 is true, Statement 2 is true [Correct Answer]
2. Statement 1 is true, Statement 2 is false
3. Statement 1 is false, Statement 2 is true
4. Statement 1 is false, Statement 2 is false
Explanation:

For sentiment analysis of Aditi's followers' comments, a rule-based approach can be implemented by
defining a set of rules to categorize the sentiment of the comments as positive, negative, or neutral. These
rules can be based on keywords or phrases commonly associated with positive or negative sentiment. For
example, a rule might be that any comment containing the words "love" or "amazing" is classified as
positive sentiment.

Scenario 2

Character: Abhimanyu, a wildlife conservationist

Task: Abhimanyu wants to track the movement of elephants in a national park to protect them from
poachers.

Statement 1: Abhimanyu can use GPS data loggers attached to the elephants' collars for this task.

Statement 2: GPS data loggers can provide real-time location information of the elephants.

Options:
1. Statement 1 is true, Statement 2 is true [Correct Answer]
2. Statement 1 is true, Statement 2 is false
3. Statement 1 is false, Statement 2 is true
4. Statement 1 is false, Statement 2 is false
Explanation:

Abhimanyu can leverage GPS data loggers attached to the elephants' collars to track their movement in the
national park. These loggers collect location data periodically, which can be transmitted wirelessly to a
central system. This real-time location information can be crucial for wildlife conservationists like
Abhimanyu to monitor the elephants' movements and take necessary actions to protect them from poachers.

Scenario 3

Character: A self-driving car company

Task: The company is developing a self-driving car that needs to make quick decisions in emergency
situations.

Statement 1: The company should use a reinforcement learning approach for this task.

Statement 2: Reinforcement learning allows the car to learn through trial and error in a simulated
environment.

Options:
1. Statement 1 is true, Statement 2 is true [Correct Answer]
2. Statement 1 is true, Statement 2 is false
3. Statement 1 is false, Statement 2 is true
4. Statement 1 is false, Statement 2 is false
Explanation:

A self-driving car navigating an emergency situation requires the ability to make quick and optimal
decisions. Reinforcement learning is a suitable approach for this task, as it allows the car to learn through
trial and error in a simulated environment. The car can be exposed to various emergency scenarios in the
simulation and learn the actions that lead to the most favorable outcomes. This simulated learning can then
be applied to real-world situations, enabling the car to make quick decisions in emergencies.

Scenario 4

Character: An online learning platform

Task: The platform wants to personalize the learning experience for each student based on their
performance.
Statement 1: The platform can use an unsupervised learning approach to cluster students with similar
learning patterns.

Statement 2: Unsupervised learning can identify patterns in data without predefined labels.

Options:
1. Statement 1 is true, Statement 2 is true [Correct Answer]
2. Statement 1 is true, Statement 2 is false
3. Statement 1 is false, Statement 2 is true
4. Statement 1 is false, Statement 2 is false
Explanation:

An online learning platform can leverage unsupervised learning to personalize the learning experience for
students. By analyzing student data, such as their performance on quizzes and assignments, the platform can
use unsupervised learning algorithms to cluster students with similar learning patterns. This allows the
platform to recommend learning materials and adjust the difficulty level based on each student's group,
thereby personalizing the learning experience.

Scenario 5

Character: A manufacturing company

Task: The company wants to predict machine failures to prevent downtime and production losses.

Statement 1: The company can use predictive modeling to address this task.

Statement 2: Predictive modeling uses historical data to identify patterns that can predict future events.

Options:
1. Statement 1 is true, Statement 2 is true [Correct Answer]
2. Statement 1 is true, Statement 2 is false
3. Statement 1 is false, Statement 2 is true
4. Statement 1 is false, Statement 2 is false
Explanation:

Predictive modeling is a powerful tool for a manufacturing company wanting to predict machine failures. By
collecting historical data on machine performance, such as sensor readings, maintenance logs, and failure
records, predictive models can be trained to identify patterns that precede machine breakdowns. Analyzing
these patterns enables the company to proactively predict potential failures, allowing them to schedule
preventative maintenance, avoid downtime, and optimize production efficiency.
Competency based very short answer type questions:

Question 1

What are the four main stages of the AI project cycle?

Answer: The four main stages of the AI project cycle are:


1. Problem Scoping.
2. Data Acquisition.
3. Data Exploration.
4. Modelling.
Question 2

What are the two main approaches to machine learning?

Answer: The two main approaches to machine learning are:


1. Rule-based learning.
2. Learning-based approach.
Question 3

What is the difference between supervised and unsupervised learning?

Answer:

Supervised learning involves training a model using labeled data, where the data is tagged with the desired
output. In contrast, unsupervised learning deals with unlabeled data, where the model identifies patterns and
relationships in the data without predefined labels.

Question 4

What are some of the benefits of using neural networks?

Answer:

Neural networks offer several benefits, including:

 Ability to handle complex patterns.


 Capability to learn and improve automatically through training on large datasets.
 Potential to extract features from data without explicit programming.
Question 5

What is one real-world application of a self-driving car?


Answer:

The chapter "class x aipc book textual.pdf" does not discuss specific applications of self-driving cars.
However, self-driving cars have the potential to revolutionize transportation by providing:

 Increased safety by reducing human error.


 Improved traffic flow and reduced congestion.
 Enhanced accessibility for people who cannot drive themselves.

Case study based very short answer type questions:

Scenario 1:

Character: A data scientist working for a company that develops self-driving cars.

Question: How can the concept of data exploration be used to improve the safety and efficiency of self-
driving cars?

Scenario 2:

Character: A farmer who wants to optimize crop yield using AI.

Question: How can the different stages of the AI project cycle be applied to develop a system that predicts
the optimal planting time for different crops based on weather data?

Scenario 3:

Character: A doctor who wants to use AI to diagnose diseases more accurately.

Question: How can neural networks be used to analyze medical images and identify patterns that may be
indicative of certain diseases?

Scenario 4:

Character: A musician who wants to compose music using AI.

Question: How can unsupervised learning be used to identify patterns in a dataset of existing music and
generate new musical pieces based on those patterns?

Scenario 5:

Character: A teacher who wants to use AI to personalize learning for students.


Question: How can supervised learning be used to analyze student data and create personalized learning
plans that cater to their individual needs and learning styles?

Remembering and Understanding questions:

Question 1:

What are the different stages of the AI project cycle?

Answer: The document defines five stages of the AI project cycle:


1. Problem Scoping.
2. Data Acquisition.
3. Data Exploration.
4. Modelling.
5. Evaluation.
Question 2:

What are the four Ws used in problem scoping in the AI project cycle?

Answer: The document explains that problem scoping uses a 4Ws approach to identify and understand the
problem. The four Ws are:
 Who.
 What.
 Where.
 Why.
Question 3:

What are the two main approaches to AI modelling?

Answer: The document outlines two main approaches to AI modelling:


1. Rule-based approach.
2. Learning-based approach.
Question 4:

What is the difference between supervised and unsupervised learning in AI modelling?

Answer: The document clarifies the difference between supervised and unsupervised learning:
 Supervised learning involves a labelled dataset where the data is pre-tagged with identifiers. The
model learns the relationship between the input and output data.
 Unsupervised learning uses unlabeled data where the model identifies patterns and trends in the
data itself.
Question 5:

What are some of the applications of neural networks mentioned in the document?

Answer: The document mentions that neural networks are used for various applications, including:
 Recognizing hidden patterns in raw data.
 Clustering and classifying data.
 Continuous learning and improvement.
 Solving problems with large datasets like images.

You might also like