Scribd
Upload
30 views2 pages

Ch3 - Question Answers-1

Uploaded by

mehularora555
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
30 views2 pages

Ch3 - Question Answers-1

Uploaded by

mehularora555
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Ch-3 AI Project Cycle

1. What is the Al project lifecycle and how is it structured?


Ans1. Problem Scoping: Define project goals, identify problems, and determine key performance indicators (KPIs).
Data Acquisition: Collect relevant data from various sources, including databases, APIs, and files.
Data Exploration: Examine and analyze data to understand patterns, relationships, and quality issues.
Modeling: Develop and train machine learning models using the prepared data to address the problem.
Evaluation: Assess the performance of the trained models using metrics such as accuracy, precision, and recall.
These stages provide a solid foundation for a data-driven AI project.

2. Explain the importance of problem scoping in the AI project lifecycle.


Ans2. Problem scoping helps identify the specific problem an AI system will address, the stakeholders involved, and the
success criteria. It ensures that the project aligns with organizational goals and avoids unnecessary resource
expenditure on irrelevant issues.

3. What is data acquisition, and why is it a crucial step in AI project development?


Ans3. Data acquisition involves gathering relevant data from various sources to train and evaluate the AI model. It is
crucial because high-quality and sufficient data directly impact the accuracy and reliability of the AI solution.

4. Describe the term "features" in the context of data in AI.


Ans4. Features are individual measurable properties or characteristics of a dataset that are used as inputs for an AI
model. They represent the aspects of the data that are most relevant to solving the problem at hand.

5. What are some common sources of data for AI projects?


Ans5. Common sources include:
Public datasets (e.g., Kaggle, UCI Machine Learning Repository)
Web scraping
APIs
Sensors and IoT devices
Company databases
Surveys and user-generated data

6. How can you determine if a data source is reliable for an AI project?


Ans6. To assess reliability, check:
Source credibility (e.g., reputable organizations)
Data accuracy and consistency
Data completeness and timeliness
Freedom from bias and errors

7. What is data exploration, and why is it essential in the AI project lifecycle?


Ans7. Data exploration involves analyzing the dataset to understand its structure, patterns, and potential issues. It is
essential because it helps identify relationships, outliers, and inconsistencies that might affect model performance.

8. What is the purpose of data visualization in data exploration?


Ans8. Data visualization presents data in graphical formats (e.g., charts, graphs) to make it easier to spot trends,
correlations, and anomalies. This enhances understanding and aids in making informed decisions about data
preprocessing and feature selection.

9. Define what a system map is and its role in AI projects.


Ans9. A system map is a visual representation of all components, processes, and stakeholders involved in an AI system.
It helps in understanding the system's workflow, identifying dependencies, and ensuring alignment with project
goals.
10. Explain the differences between Artificial Narrow Intelligence (ANI), Artificial General Intelligence (AGI), and Artificial
Superintelligence (ASI).
Ans10.
ANI: Specialized AI designed for a specific task .
AGI: AI with the ability to perform any intellectual task a human can. It has general learning and reasoning abilities.
ASI: Hypothetical AI surpassing human intelligence in all domains, capable of autonomous learning and decision-making.

11. What is the primary goal of the modeling phase in the AI project lifecycle? Explain the difference between rule-based
AI and learning-based AI.
Ans11. The goal is to create a predictive model using algorithms that best solve the defined problem.
Rule-based AI: Operates on predefined rules and logic.
Learning-based AI: Learns patterns from data and adjusts dynamically to new inputs.

12. Why is evaluation important in AI projects, and when does it typically occur?
Ans12. Evaluation ensures that the AI model meets performance criteria and is ready for deployment. It typically occurs
after training and testing but may also be conducted during iterative improvements.

13. What are decision trees in AI, and for what types of tasks are they commonly used?
Ans13. Decision trees are flowchart-like models used for classification and regression tasks. They split data into branches
based on feature values, making them easy to interpret.

14. Describe the concept of overfitting in AI models.


Ans14. Overfitting occurs when an AI model learns not just the underlying patterns but also the noise in the training
data, leading to poor generalization on new data.

15. What is the main purpose of deploying an AI model? When does deployment typically happen in the AI project
lifecycle?
Ans15. Deployment makes the trained model operational, allowing it to provide insights or automation in real-world
scenarios. It typically happens after successful evaluation and testing phases.

You might also like