Curriculum
Grade X AI(417)
Lessons
0/7
Notes
0/7
WorkSheets
0/7
All Notes and All Worksheets
0/2
Unit 7-Evaluation
School Revise · Class 10 Artificial Intelligence · Unit 7
Evaluation
Code 417, Class 10. We must check how good an AI model is. Here we learn accuracy, the confusion matrix, precision and recall.
|
|
What this unit is about
Evaluation checks how well an AI model works on new data, so we know if we can trust it.
1. Accuracy
Accuracy is how often the model is correct: the number of correct predictions divided by the total. High accuracy on new data is a good sign.
|
If 8 out of 10 predictions are correct: accuracy = 8 / 10 = 0.8 or 80% |
2. The confusion matrix
A confusion matrix counts four cases: True Positive, True Negative (both correct), and False Positive, False Negative (both wrong). It shows where the model goes wrong.
3. Precision and recall
Precision asks: of the items the model called positive, how many really were. Recall asks: of the real positive items, how many the model found. Both help judge a model beyond accuracy.
Practise with the interactive
Explore the idea by tapping. The interactive opens right here in the lesson.
Practice set A, multiple choice
1. How often a model is correct is its …
accuracy.
2. A table of correct and wrong predictions is a …
confusion matrix.
3. A correct positive prediction is a …
True Positive.
4. A wrong positive prediction is a …
False Positive.
Practice set B, short answer
1. What is accuracy?
How often the model is correct: correct predictions divided by the total.
2. What is a confusion matrix?
A table that counts true and false positives and negatives.
3. What is the difference between precision and recall?
Precision is how many predicted positives were right; recall is how many real positives were found.
Quick summary
|
Evaluation checks how well a model works on new data. Accuracy is how often it is correct (correct divided by total). A confusion matrix counts True Positive, True Negative, False Positive and False Negative, showing where the model goes wrong. Precision is how many predicted positives were right, and recall is how many real positives were found; both judge a model beyond accuracy. |
| Open the Virtual Lab |
These free Class 10 Artificial Intelligence (Code 417) notes explain evaluating AI models, accuracy, the confusion matrix, and precision and recall with clear examples and practice, for CBSE students across India and the Gulf including the UAE, Saudi Arabia, Qatar, Oman, Kuwait and Bahrain.
© 2026 School Revise. All rights reserved. Original content aligned to the CBSE and NCERT Class 10 Artificial Intelligence syllabus. Unauthorised copying is not permitted.
Google