Artificial Intelligence Worksheet – Class X
Topics: NLP | Computer Vision | Evaluation | ICT Skills
---
Section A: Multiple Choice Questions
(Attempt all questions)
1. What is the main goal of Natural Language Processing?
a) To process numeric data
b) To enable computers to understand human language
c) To compress large data
d) To translate binary language to English
2. Which of the following is not a component of NLP?
a) Tokenization
b) Edge Detection
c) Lemmatization
d) Named Entity Recognition
3. Optical Character Recognition (OCR) is a part of:
a) NLP
b) Robotics
c) Computer Vision
d) None of the above
4. Which is an example of computer vision in daily life?
a) Email spam detection
b) Face recognition in smartphones
c) Chatbots
d) Auto-correct feature
5. F1-Score is a metric used to evaluate a model based on:
a) Precision and recall
b) Accuracy and loss
c) Confusion and clarity
d) Speed and memory
6. What does ICT stand for?
a) Internet and Communication Technology
b) Information and Computer Technology
c) Information and Communication Technology
d) Inter-Computer Transmission
7. Which of the following is used to evaluate an AI model’s overall correctness?
a) Precision
b) Recall
c) Accuracy
d) F1 Score
8. In NLP, removing stop words is part of:
a) Machine Translation
b) Text Preprocessing
c) Speech-to-text conversion
d) Syntax checking
9. Which of these is a challenge in Computer Vision?
a) Lack of labeled data
b) Too many users
c) Internet bandwidth
d) Power supply
10. Which ICT skill helps in creating digital presentations?
a) Word processing
b) Spreadsheet management
c) Presentation tools
d) Data visualization
11. What is recall in AI evaluation?
a) % of correctly predicted negative instances
b) % of total predictions that were correct
c) % of actual positives that were correctly identified
d) None of the above
12. In NLP, POS tagging refers to:
a) Prediction of sentence tags
b) Parts of speech tagging
c) Position of sounds
d) Page order specification
13. A confusion matrix helps in:
a) Understanding user intent
b) Evaluating classification models
c) Detecting emotions
d) None of the above
14. Which of the following is not an input for a Computer Vision system?
a) Images
b) Videos
c) Sound
d) Depth Maps
15. Precision in model evaluation is:
a) TP / (TP + FP)
b) TP / (TP + FN)
c) FP / (TP + TN)
d) TN / (FP + FN)
---
Section B: Long Answer Questions
(Attempt any five)
1. Explain how NLP is used in real life with examples.
Include at least three applications and their related AI techniques.
2. Describe the process of image classification in computer vision.
Mention the role of training data and model evaluation.
3. Differentiate between precision, recall, accuracy, and F1-score using formulas and
examples.
4. Explain how ICT skills support artificial intelligence development and use in schools.
Include examples and tools used in classrooms.
5. Compare and contrast NLP and Computer Vision.
Highlight their input data, techniques used, and common challenges.
---
Section C: Model Evaluation Numericals
(Solve the following based on the data provided)
1. A model classified emails as spam or not spam:
True Positives (TP) = 60
False Positives (FP) = 20
False Negatives (FN) = 10
True Negatives (TN) = 110
Calculate:
a) Precision
b) Accuracy
2. A face recognition system gave the following results:
TP = 90
FP = 10
FN = 30
Calculate:
a) Recall
b) F1-Score
3. In a sentence classification model:
Total predictions = 100
Correct predictions = 88
Find the accuracy.
4. A disease prediction AI model gave:
TP = 50
FP = 15
FN = 20
TN = 115
Calculate:
a) Recall
b) Accuracy
5. Consider a confusion matrix where:
TP = 30, FP = 10, FN = 5, TN = 55
Calculate:
a) Precision
b) F1 Score
