Certification IN ARTIFICIAL INTELLIGENCE ( S-AYN95 )

Artificial Intelligence (AI) Syllabus

Module 1: Introduction to AI

• Definition, Goals, and Applications of AI
• History of AI and Current Trends
• Weak vs. Strong AI

Module 2: Problem Solving and Search

• State Space Search
• Uninformed Search: BFS, DFS
• Informed Search: A*, Heuristic Functions
• Adversarial Search: Minimax, Alpha-Beta Pruning

Module 3: Knowledge Representation

• Logic: Propositional and Predicate Logic
• Semantic Networks and Frames
• Ontologies and Expert Systems

Module 4: Machine Learning Basics

• Types of Machine Learning: Supervised, Unsupervised, Reinforcement
• Regression and Classification Basics
• Clustering Algorithms (K-Means, Hierarchical)
• Introduction to Neural Networks

Module 5: Reasoning and Decision Making

• Probabilistic Reasoning: Bayes’ Theorem, Bayesian Networks
• Fuzzy Logic
• Markov Decision Processes

Module 6: Natural Language Processing (NLP)

• Language Models
• Text Preprocessing Techniques
• Sentiment Analysis and Chatbots
• Basics of Speech Recognition

Module 7: Robotics and Perception

• Basics of Robotics and Sensors
• Path Planning and Localization
• Computer Vision: Image Processing, Object Detection

Module 8: AI Tools and Frameworks

• Introduction to TensorFlow and PyTorch
• Scikit-learn for Machine Learning
• OpenCV for Computer Vision

Module 9: Ethics and Future of AI

• Ethical Considerations in AI
• Bias in AI Systems
• Future Directions and Challenges

Module 10: AI Applications

• AI in Healthcare, Finance, and Education
• Autonomous Systems and Smart Assistants
• Real-World Case Studies

10th Pass