Artificial Intelligence Syllabus

1.1 Fundamentals of AI

• 1.1.1 Definitions, Goals, and Approaches
• 1.1.2 Historical Evolution (1950s–Present)
• 1.1.3 AI Techniques: Symbolic vs. Subsymbolic Methods

1.2 Challenges in AI

• 1.2.1 Technical Barriers (Scalability, Data Quality)
• 1.2.2 Philosophical Debates (Consciousness, Ethics)
• 1.2.3 The Turing Test and Modern Alternatives (e.g., CAPTCHAs)

1.3 Applications

• 1.3.1 Healthcare (Diagnostic Systems)
• 1.3.2 Autonomous Systems (Self-Driving Cars)
• 1.3.3 Business Analytics (Fraud Detection)
• 1.3.4 AI for Social Good (Climate Modeling, Disaster Response)

1.4 Lab: Python/Prolog Basics for AI

• 1.4.1 Syntax and Data Structures
• 1.4.2 Introduction to Jupyter Notebooks and Prolog Environments
• 1.4.3 Setting up AI Development Environments (TensorFlow, PyTorch)

2.1 Agent Architecture

• 2.1.1 Rational Agents vs. Omniscient Agents
• 2.1.2 PEAS Framework (Performance, Environment, Actuators, Sensors)
• 2.1.3 Agent Design Patterns and Architectures

2.2 Environment Types

• 2.2.1 Observable vs. Partially Observable
• 2.2.2 Deterministic vs. Stochastic
• 2.2.3 Episodic vs. Sequential
• 2.2.4 Static vs. Dynamic
• 2.2.5 Discrete vs. Continuous

2.3 Agent Types

• 2.3.1 Reflex Agents (Simple, Model-Based)
• 2.3.2 Goal-Based Agents
• 2.3.3 Utility-Based Agents
• 2.3.4 Learning Agents
• 2.3.5 Multi-Agent Systems

2.4 Lab: Agent Simulation

• 2.4.1 Implement a Vacuum-Cleaner Agent (Python)
• 2.4.2 PEAS Design for a Delivery Robot
• 2.4.3 Multi-Agent Coordination Simulation

3.1 Uninformed Search

• 3.1.1 Breadth-First Search (BFS)
• 3.1.2 Depth-First Search (DFS)
• 3.1.3 Uniform Cost Search
• 3.1.4 Iterative Deepening
• 3.1.5 Complexity Analysis (Time/Space)

3.2 Informed Search

• 3.2.1 Greedy Best-First Search
• 3.2.2 A* Algorithm
• 3.2.3 Admissible Heuristics
• 3.2.4 Iterative Deepening A* (IDA*)
• 3.2.5 Memory-Bounded Search (SMA*, RBFS)

3.3 Adversarial Search

• 3.3.1 Minimax Algorithm
• 3.3.2 Alpha-Beta Pruning
• 3.3.3 Game Trees for Tic-Tac-Toe and Chess
• 3.3.4 Expectimax Search for Stochastic Games
• 3.3.5 Monte Carlo Tree Search (MCTS)

3.4 Lab: Search Algorithms

• 3.4.1 Implement BFS/DFS for Maze Solving
• 3.4.2 Build a Tic-Tac-Toe AI with Minimax
• 3.4.3 Develop a Pathfinding Algorithm with A*
• 3.4.4 MCTS Implementation for Simple Games

4.1 Logic-Based Systems

• 4.1.1 Propositional Logic
• 4.1.2 First-Order Logic
• 4.1.3 Resolution and Inference Rules
• 4.1.4 Unification and Substitution
• 4.1.5 Theorem Proving

4.2 Structured Knowledge

• 4.2.1 Semantic Networks
• 4.2.2 Ontologies and Knowledge Graphs
• 4.2.3 Rule-Based Systems (Forward Chaining)
• 4.2.4 Rule-Based Systems (Backward Chaining)
• 4.2.5 Frames and Scripts

4.3 Probabilistic Reasoning

• 4.3.1 Bayesian Networks
• 4.3.2 Markov Models and Hidden Markov Models
• 4.3.3 Probabilistic Graphical Models
• 4.3.4 Exact and Approximate Inference
• 4.3.5 Decision Networks and Utility Theory

4.4 Lab: Knowledge Representation Systems

• 4.4.1 Prolog for Family Tree Relationships
• 4.4.2 Expert System for Medical Diagnosis
• 4.4.3 Building a Bayesian Network for Risk Assessment
• 4.4.4 Knowledge Graph Implementation

5.1 Supervised Learning

• 5.1.1 Linear and Logistic Regression
• 5.1.2 Decision Trees (ID3, C4.5, CART)
• 5.1.3 Support Vector Machines
• 5.1.4 Neural Networks (Perceptrons, Backpropagation)
• 5.1.5 Ensemble Methods (Random Forests, Boosting)

5.2 Unsupervised Learning

• 5.2.1 K-Means Clustering
• 5.2.2 Hierarchical Clustering
• 5.2.3 PCA for Dimensionality Reduction
• 5.2.4 Association Rule Learning
• 5.2.5 Anomaly Detection

5.3 Deep Learning

• 5.3.1 Feedforward Neural Networks
• 5.3.2 Convolutional Neural Networks (CNNs)
• 5.3.3 Recurrent Neural Networks (RNNs)
• 5.3.4 Long Short-Term Memory (LSTM)
• 5.3.5 Transfer Learning and Fine-Tuning

5.4 Reinforcement Learning

• 5.4.1 Markov Decision Processes
• 5.4.2 Q-Learning and SARSA
• 5.4.3 Policy Gradient Methods
• 5.4.4 Deep Reinforcement Learning (DQN, A3C)
• 5.4.5 Multi-Agent Reinforcement Learning

5.5 Lab: Machine Learning Implementation

• 5.5.1 Train a Classifier on MNIST Dataset
• 5.5.2 Implement a Neural Network from Scratch
• 5.5.3 Transfer Learning with Pre-trained Models
• 5.5.4 Reinforcement Learning for Game Playing
• 5.5.5 ML Model Optimization and Deployment

6.1 Foundations

• 6.1.1 Tokenization and Word Embeddings
• 6.1.2 POS Tagging and Parsing
• 6.1.3 Named Entity Recognition
• 6.1.4 Sequence-to-Sequence Models
• 6.1.5 Attention Mechanisms

6.2 Advanced NLP Models

• 6.2.1 Transformer Architecture
• 6.2.2 BERT and Contextual Embeddings
• 6.2.3 GPT and Large Language Models
• 6.2.4 Zero-shot and Few-shot Learning
• 6.2.5 Multilingual Models

6.3 Applications

• 6.3.1 Sentiment Analysis
• 6.3.2 Machine Translation
• 6.3.3 Question Answering
• 6.3.4 Text Summarization
• 6.3.5 Conversational AI

6.4 Lab: NLP Tasks

• 6.4.1 Text Classification with HuggingFace
• 6.4.2 Fine-tuning BERT for Custom Tasks
• 6.4.3 Building a Text Summarization System
• 6.4.4 Chatbot Development (Rasa/Dialogflow)
• 6.4.5 Multilingual NLP Application

7.1 Foundations

• 7.1.1 Variational Autoencoders (VAEs)
• 7.1.2 Generative Adversarial Networks (GANs)
• 7.1.3 Diffusion Models
• 7.1.4 Autoregressive Models
• 7.1.5 Energy-Based Models

7.2 Applications

• 7.2.1 Image Generation (DALL-E, Stable Diffusion)
• 7.2.2 Text-to-Image Synthesis
• 7.2.3 Music and Audio Generation
• 7.2.4 Text Generation and Completion
• 7.2.5 Multimodal Generation

7.3 Lab: Generative Models

• 7.3.1 Building a Simple GAN
• 7.3.2 Fine-tuning Pre-trained Generative Models
• 7.3.3 Implementing a Text-to-Image System
• 7.3.4 Creating a Music Generation Application
• 7.3.5 Evaluating Generative Model Outputs

8.1 Fundamentals of Expert Systems

• 8.1.1 Human Expert vs Expert System
• 8.1.2 Expert System Structure and Architecture
• 8.1.3 Characteristics of Expert Systems
• 8.1.4 Comparison with Traditional Software
• 8.1.5 Historical and Modern Expert Systems

8.2 Knowledge Engineering

• 8.2.1 Knowledge Acquisition Techniques
• 8.2.2 Knowledge Base Organization
• 8.2.3 Types of Knowledge (Declarative, Procedural)
• 8.2.4 Knowledge Representation for Expert Systems
• 8.2.5 Uncertainty Handling in Expert Systems

8.3 Inference Mechanisms

• 8.3.1 Forward Chaining
• 8.3.2 Backward Chaining
• 8.3.3 Mixed Chaining Strategies
• 8.3.4 Inference with Uncertainty
• 8.3.5 Explanation Facilities

8.4 Lab: Expert System Development

• 8.4.1 Tools for Expert System Development (CLIPS, Prolog)
• 8.4.2 Building a Simple Medical Diagnosis System
• 8.4.3 Knowledge Acquisition Exercise
• 8.4.4 Rule-Based System Implementation
• 8.4.5 Testing and Evaluating Expert Systems

9.1 Fundamentals of Computer Vision

• 9.1.1 Image Formation and Representation
• 9.1.2 Digital Image Processing Basics
• 9.1.3 Color Models and Spaces
• 9.1.4 Feature Extraction Techniques
• 9.1.5 Historical Development of Computer Vision

9.2 Image Analysis

• 9.2.1 Edge Detection (Sobel, Canny)
• 9.2.2 Line and Shape Detection (Hough Transform)
• 9.2.3 Image Segmentation Methods
• 9.2.4 Texture Analysis
• 9.2.5 Motion Analysis and Optical Flow

9.3 Object Recognition

• 9.3.1 Template Matching
• 9.3.2 Feature-Based Recognition
• 9.3.3 Deep Learning for Object Detection
• 9.3.4 Instance vs. Semantic Segmentation
• 9.3.5 3D Scene Understanding

9.4 Advanced Topics

• 9.4.1 Face Detection and Recognition
• 9.4.2 Activity and Gesture Recognition
• 9.4.3 Visual SLAM (Simultaneous Localization and Mapping)
• 9.4.4 Augmented Reality Applications
• 9.4.5 Vision for Robotics

9.5 Lab: Computer Vision Applications

• 9.5.1 Image Processing with OpenCV
• 9.5.2 Implementing Basic Edge and Object Detectors
• 9.5.3 CNN-Based Object Recognition
• 9.5.4 Building a Face Recognition System
• 9.5.5 Real-time Computer Vision Application

10.1 Fundamentals of CSPs

• 10.1.1 Formal Definition and Examples
• 10.1.2 Constraint Types and Representations
• 10.1.3 Variables, Domains, and Constraints
• 10.1.4 Complexity Analysis of CSPs
• 10.1.5 Relationship to Search Problems

10.2 CSP Solving Techniques

• 10.2.1 Backtracking Search
• 10.2.2 Constraint Propagation
• 10.2.3 Arc Consistency Algorithms
• 10.2.4 Forward Checking
• 10.2.5 Minimum Remaining Values and Degree Heuristics

10.3 Advanced CSP Methods

• 10.3.1 Local Search for CSPs
• 10.3.2 Genetic Algorithms for CSPs
• 10.3.3 Distributed CSPs
• 10.3.4 Soft Constraints and Optimization
• 10.3.5 Temporal and Dynamic CSPs

10.4 Lab: CSP Applications

• 10.4.1 Implementing Cryptarithmetic Solvers
• 10.4.2 N-Queens Problem Implementation
• 10.4.3 Sudoku Solver Development
• 10.4.4 Scheduling Problem Applications
• 10.4.5 Building a CSP Framework

11.1 Ethical Frameworks

• 11.1.1 Consequentialism, Deontology, and Virtue Ethics
• 11.1.2 Bias Detection and Mitigation in ML Models
• 11.1.3 Fairness Metrics and Algorithmic Justice
• 11.1.4 Transparency and Explainability
• 11.1.5 Data Privacy and Consent (GDPR, CCPA)

11.2 Responsible AI Development

• 11.2.1 Human-Centered AI Design
• 11.2.2 Accountability and Governance
• 11.2.3 Safety and Alignment
• 11.2.4 Environmental Impact of AI Systems
• 11.2.5 AI in Critical Infrastructure

11.3 Case Studies

• 11.3.1 Autonomous Weapons Debate
• 11.3.2 Algorithmic Fairness in Hiring
• 11.3.3 AI in Healthcare Decision-Making
• 11.3.4 Surveillance Technologies
• 11.3.5 Synthetic Media and Misinformation

11.4 Lab: Ethics Workshop

• 11.4.1 Auditing a Dataset for Bias
• 11.4.2 Developing Explainable AI Methods
• 11.4.3 Design an Ethical AI Policy
• 11.4.4 Building a Fairness-Aware Model
• 11.4.5 Ethics Impact Assessment for AI Projects

12.1 Guidelines

• 12.1.1 Topic Selection and Approval Process
• 12.1.2 Milestones: Proposal, Design, Prototype, Demo
• 12.1.3 Documentation and Presentation Requirements
• 12.1.4 Evaluation Criteria

12.2 Suggested Topics

• 12.2.1 AI for Climate Modeling and Sustainability
• 12.2.2 AI-Driven Educational Tools
• 12.2.3 Healthcare Predictive Analytics
• 12.2.4 Personalized Recommendation Systems
• 12.2.5 Computer Vision for Accessibility
• 12.2.6 Natural Language Understanding Applications
• 12.2.7 Robotics and Autonomous Systems
• 12.2.8 AI for Creative Expression
• 12.2.9 Expert System Development
• 12.2.10 CSP Applications in Real-world Problems