Introduction to Artificial Intelligence

Description

Introduction to Artificial Intelligence – Curriculum Outline

Course Duration: 12–15 Weeks

Prerequisites:

• Basic Python programming
• Linear algebra, calculus, probability
• Logic and discrete math (recommended)

---

🗂️ Module-wise Breakdown

Module 1: Introduction to AI

• What is AI? History and evolution
• AI vs ML vs Deep Learning
• Applications of AI (healthcare, robotics, NLP, games, etc.)
• Ethical and societal implications

---

Module 2: Intelligent Agents

• Agents and environments
• Rationality
• Types of agents: simple reflex, goal-based, utility-based, learning agents

---

Module 3: Problem Solving and Search

• Problem formulation
• Uninformed search (BFS, DFS, UCS)
• Informed search (Greedy, A*)
• Search optimization strategies

---

Module 4: Knowledge Representation and Reasoning

• Propositional logic
• First-order logic
• Inference in logic systems
• Knowledge-based agents

---

Module 5: Planning

• Classical planning
• Planning graphs
• Hierarchical task networks
• Partial order planning

---

Module 6: Constraint Satisfaction Problems (CSP)

• Definitions and examples
• Backtracking and heuristics
• Local search for CSPs (e.g. min-conflicts)

---

Module 7: Machine Learning Basics

• Supervised vs Unsupervised learning
• Basic algorithms: Linear regression, k-NN, decision trees
• Overfitting, underfitting, and cross-validation

---

Module 8: Neural Networks and Deep Learning

• Introduction to neural networks
• Backpropagation
• Convolutional Neural Networks (CNNs)
• Applications in image and speech recognition

---

Module 9: Natural Language Processing (NLP)

• Text representation: Bag of Words, TF-IDF, word embeddings
• Basic NLP tasks: sentiment analysis, text classification
• Language models and transformers (overview)

---

Module 10: Robotics and Perception

• AI in robotics
• Localization and mapping
• Perception and computer vision basics

---

Module 11: Reinforcement Learning

• Markov Decision Processes (MDPs)
• Q-learning and policy learning
• Applications in gaming and autonomous agents

---

Module 12: Ethics and Future of AI

• Bias and fairness
• Privacy and surveillance
• Explain ability
• The future of work and AI governance

---

🧪 Assessment Components

• Quizzes and assignments
• Labs and practical projects
• Midterm exam
• Final project (e.g. build an AI-based chatbot, game AI, or ML model)