Page 255 - Artificial Intellegence_v2.0_Class_9
P. 255
10. Identify the data features, collect the data and convert into graphical representation. Also, collect and
store data in a spreadsheet and create some graphical representations to understand the data effectively.
11. Create and present the neural networks on a cardboard/chart paper for classifying images of animals?
Collaborate to create your network and explain how it works!"
Class Activity Interdisciplinary
Logistics: For a class of 40 Students. [Group Activity – Groups of 4] [CBSE Handbook]
Materials Required:
ITEM QUANTITY
Computers 10
Resources:
Link to visualisation website: https://datavizcatalogue.com/
Purpose: To understand why we do data exploration before jumping straight into training an AI Model.
Say: “Why do you think we need to explore and visualise data before jumping into the AI model? When
we pick up a library book, we tend to look at the book cover, read the back cover and skim through the
content of the book prior to choosing it as it helps us understand if this book is appropriate for our needs
and interests. Similarly, when we get a set of data in our hands, spending time to explore it will help get a
sense of the trends, relationships and patterns present in the data. It will also help us better decide on which
model/models to use in the subsequent AI Project Cycle stage. We use visualization as a method because it
is much easier to comprehend information quickly and communicate the story to others.”
Brief:
In this session, we will be exploring various types of Graphs using an online open- sourced website. Students
will learn about various new ways to visualise the data.
When to intervene?
Ask the students to figure out which types of graphs would be suitable for the data features that they have
listed for their problem. Let them take their time in going through each graph and its description and decide
which one suits their needs the best.
Answers
Exercise (Section A)
A. 1. b 2. c 3. b 4. c 5. a 6. c 7. c 8. a 9. c 10. a
11. b 12. a 13. d 14. a 15. a
B. 1. Data 2. Training data 3. Surveys 4. third stage 5. automated tools/manual methods
6. Data visualization 7. branches 8. subset 9. binary 10. mathematical
C. 1. False 2. True 3. True 4. False 5. False 6. False 7. True 8. True 9. True 10. False
11. True 12. True 13. False 14. False 15. True
D. 1. c 2. a 3. b 4. e 5. d 6. g 7. f 8. i 9. h
AI Project Cycle 253

