CLASS 10 AI – ADVANCED CONCEPTS OF MODELLING
DETAILED NOTES (UNIT 2.1 & 2.2)
--------------------------------------------
2.1 Revisiting AI, ML and DL
--------------------------------------------
➤ Artificial Intelligence (AI)
AI is the ability of machines to perform tasks that normally require human intelligence
such as decision■making, problem■solving, pattern recognition, understanding language.
➤ Machine Learning (ML)
ML is a sub■field of AI where machines learn from data and improve their performance
without being explicitly programmed.
➤ Deep Learning (DL)
DL is an advanced form of ML that uses artificial neural networks with many layers to
learn complex patterns from huge amounts of data.
➤ Difference between AI, ML and DL
• AI is the broader concept → machines showing intelligence.
• ML is a sub■set of AI → machines learn from data.
• DL is a sub■set of ML → uses neural networks to learn deeply from big data.
➤ Common Terminologies Used with Data
• Data: Raw facts (images, numbers, text).
• Dataset: Collection of data.
• Features: Input variables used by a model (example: height, marks).
• Labels/Target: Output variable to be predicted.
• Training Data: Data used to train the model.
• Testing Data: Data used to evaluate model performance.
--------------------------------------------
2.2 Modelling
--------------------------------------------
Modelling means creating a mathematical or logical system (model) that can make
predictions, identify patterns or take decisions based on data.
--------------------------------------------
➤ Types of AI Models
--------------------------------------------
1. Rule■Based Models
• Use a set of predefined rules (IF■THEN statements).
• Example: IF marks > 90 THEN grade = A.
2. Learning■Based Models
• Learn from data instead of rules.
• Example: Predicting price of a house based on previous data.
--------------------------------------------
➤ Categories of Machine Learning Based Models
--------------------------------------------
1. Supervised Learning
• Model is trained on labeled data (input + output).
• Example: Classifying emails as spam/not spam.
Sub■categories:
• Classification – Predicting categories (Pass/Fail, Cat/Dog).
• Regression – Predicting continuous values (Temperature, price).
2. Unsupervised Learning
• Model learns from unlabeled data.
• Finds patterns and structures in data.
Sub■categories:
• Clustering – Grouping items based on similarity (customers with similar behaviour).
• Association – Finding relationships (people who buy bread also buy butter).
3. Reinforcement Learning
• Model learns by interacting with the environment.
• Learns from rewards and penalties.
• Example: Game■playing bots, robotics.
--------------------------------------------
➤ Summary
--------------------------------------------
• AI includes ML; ML includes DL.
• Models can be rule■based or data■based.
• ML models are supervised, unsupervised or reinforcement.
• Classification, regression, clustering, association → important sub■topics.
--------------------------------------------
These notes cover the complete syllabus of Unit 2.1 and 2.2 in simple, exam■friendly language.