Subject - Artificial Intelligence

Unit – 1 – Introduction to AI
Answer the following:
1. What is intelligence?
2. Explain types of Intelligences.
3. Define the term Artificial Intelligence?
4. Explain how machines become Artificially Intelligent.
5. Explain applications of AI.
6. Explain the difference between AI, ML and DL.
7. Explain three domains of AI with an example.
8. Explain AI ethics.
9. 10. List 3 characteristics of structured and unstructured data with an example.
11. Explain the following:
a. Data privacy b. AI Bias c. AI Access d. Ethics e. AI Ethics f. Unethical AI
Unit – 2 – AI Project Cycle
Answer the following questions:
1. Explain stages of AI project cycle.
2. Explain 4Ws Problem Canvas with an example.
3. Explain Problem Statement Template with an example.
4. Explain various classifications of AI model.
5. Explain the term Neural Network with diagram.
6. Mention the features of Neural Network.
7. Differentiate between Rule Based Approach and Learning based approach.
8. What is the role of data acquisition and data exploration in any AI project?
9. Create a 4W Project Canvas for corona virus.
Unit – 4 – Data Science
1. Explain the applications of Data Science.
Unit – 5 – Computer Vision
1. Explain the applications of computer vision with examples.
2. Explain the various tasks of computer vision.
3. Explain the following terms :
a. Pixels b. Resolution c. Pixel value d. Grayscale Images e. RGB Images
Unit-6 Natural Language Processing
1. What is NLP? Explain with an example.
2. Explain Applications of Natural Language Processing ( w.r.t. Automatic Summarization,
Sentiment Analysis, Text classification and Virtual Assistants).
3. What is CBT? Write about the goal of the project.
4. Explain about the CBT project cycle.
5. Explain 4Ws of problem scoping.
6. How are overfit, underfit and perfectfit related to Evaluation?
7. What is chat-bot? State the concept used in its implementation.
8. Which chatbot did you try? Name it.
a. What is the purpose of this chatbot?
b. How was the interaction with the chatbot?
c. Did the chat feel like talking to a human or a robot? Why do you think so?
d. Do you feel that the chatbot has a certain personality?
9. Write about 2 types of chatbots around us.
10. Differentiate between Script-bot and Smart-bot.
11. Explain the concept of following with respect to Computer Language processing:
a. How are Human Language and Computer Language processed?
b. Analogy with programming language.
c. “Multiple Meanings of a word in NLP” Justify.
d. Perfect Syntax, no Meaning.
12. Explain Text Normalization part of Data Processing.
13. What is corpus? Is it important? Justify.
14. Explain Text normalization from documents to bag of words.
15. What are stop words? Give 4 examples.
16. “Lemmatization is difficult process compared to Stemming” Explain with example.
17. Differentiate between Lemmatization and Stemming.
18. “The bag of words gives us two things”, what are they?
Ans. 1. A vocabulary of words for the corpus
2. The frequency of these words (number of times it has occurred in the whole
corpus).
 19. Explain the step-by-step approach to implement bag of words algorithm.
20. Build the document vector table for corpus of your choice.
21. What is token?
22. What is document vector table?
23. How is NLP related to AI? Write its importance.
Unit- 7 Evaluation
1. What is evaluation?
2. 2. What is confusion matrix?
3. List the evaluation methods.
4. Explain Accuracy, Prediction and Recall.
5. Which Metric is Important to evaluate AI model? Any one example.
Choosing between Precision and Recall depends on the condition in which the model
has been deployed.
 In a case like Forest Fire, a False Negative can cost us a lot and is risky too.
Imagine no alert being given even when there is a Forest Fire. The whole forest
might burn down.
 Another case where a False Negative can be dangerous is Viral Outbreak. Imagine a
deadly virus has started spreading and the model which is supposed to predict a
viral outbreak does not detect it. The virus might spread widely and infect a lot of
people.
 On the other hand, there can be cases in which the False Positive condition costs
us more than False Negatives.
 One such case is Mining. Imagine a model telling you that there exists treasure at a
point and you keep on digging there but it turns out that it is a false alarm. Here,
False Positive case (predicting there is treasure but there is no treasure) can be
very costly.
 Similarly, let’s consider a model that predicts that a mail is spam or not. If the
model always predicts that the mail is spam, people would not look at it and
eventually might lose important information.
 Here also False Positive condition (Predicting the mail as spam while the mail is not
spam) would have a high cost.
For some cases, you might have a High Precision but Low Recall or Low Precision but High
Recall. But since both the measures are important, there is a need of a parameter which
takes both Precision and Recall into account i.e F1 Score
6. “Recall and Precision, both are important metrics to evaluate AI model” Justify
7. “A model has good performance if the F1 Score for that model is high” Explain
8. What is F1 score? How is it related to evaluation?
9. Calculate F1 score and compare it with accuracy for the following:
a. TP=22 TN=118 FP=12 FN=47
b. TP=0 TN=94 FP=3 FN=3
c. TP=5 TN=50 FP=0 FN=45
d. TP=50 TN=0 FP=50 FN=0
e. TP=75 TN=75 FP=75 FN=75