Class 10

Course Objectives Assessment: ● Continuous assessment through projects, quizzes, presentations, and participation. ● Emphasis on understanding and applying concepts, not just memorization. ● Project-based ... Show more
Instructor
The Kavach
0
0 reviews
  • Description
high

Chapter 1: Introduction to AI & ML
1. What is intelligence?
2. Demystifying AI terminology (algorithms, data, robots)
3. Understanding different types of AI (Supervised, Unsupervised, Reinforcement)
4. Real-world applications of AI in various fields
5. Introduction to Python programming for AI
6. Activity: Identify AI in everyday life (e.g., virtual assistants, facial recognition)
7. Activity: Write a simple Python program using basic commands
8. Activity: Debate the ethical implications of AI

Chapter 2: Data for AI
1. Importance of data in AI
2. Different data types (numerical, categorical, textual)
3. Data collection methods and ethical considerations
4. Data preprocessing and cleaning techniques
5. Data visualization tools and techniques
6. Activity: Collect and analyze data on a topic of interest
7. Activity: Use data visualization tools to create charts and graphs
8. Activity: Discuss the importance of responsible data collection

Chapter 3: Supervised Learning
1. Regression algorithms (Linear Regression, Logistic Regression)
2. Classification algorithms (Decision Trees, K-Nearest Neighbors)
3. Model evaluation metrics (accuracy, precision, recall)
4. Building and training supervised learning models with Python libraries (Scikit-learn)
5. Activity: Predict housing prices using linear regression
6. Activity: Classify handwritten digits using K-Nearest Neighbors
7. Activity: Compare and contrast different evaluation metrics

Chapter 4: Unsupervised Learning
1. Clustering algorithms (K-Means, Hierarchical Clustering)
2. Dimensionality reduction techniques (PCA)
3. Anomaly detection methods
4. Applications of unsupervised learning in real-world scenarios
5. Activity: Cluster customer data based on purchase patterns
6. Activity: Use PCA to reduce image dimensionality
7. Activity: Design an anomaly detection system for sensor data

Chapter 5: Reinforcement Learning
1. Reinforcement Learning principles (rewards, actions, states)
2. Q-Learning and Deep Q-Learning algorithms
3. Applications of Reinforcement Learning in robotics and games
4. Ethical considerations of using Reinforcement Learning
5. Activity: Train an AI agent to play a simple game
6. Activity: Discuss the potential risks and benefits of Reinforcement Learning
7. Activity: Research recent advancements in Reinforcement Learning

Chapters 6-10 (similar structure):
● Chapter 6: Introduction to Deep Learning (Neural Networks)
● Chapter 7: Natural Language Processing (NLP)
● Chapter 8: Computer Vision
● Chapter 9: Advanced AI Concepts (Generative Models, Explainable AI)
● Chapter 10: AI Project Design and Development

Activities:
● Each chapter will have engaging activities that reinforce learning, encourage critical thinking, and promote creativity.
● Examples include:
○ Hands-on coding projects using Python libraries
○ Data analysis and visualization tasks
○ Research and presentations on specific AI applications
○ Debates and discussions on ethical issues
○ Designing and developing their own AI project

Assessment:
● Continuous assessment through projects, quizzes, presentations, and participation.
● Emphasis on understanding and applying concepts, not just memorization.
● Project-based learning will be a key element of the assessment.

Archive

Working hours

Monday 9:30 am - 6.00 pm
Tuesday 9:30 am - 6.00 pm
Wednesday 9:30 am - 6.00 pm
Thursday 9:30 am - 6.00 pm
Friday 9:30 am - 5.00 pm
Saturday Closed
Sunday Closed