CMP346 Artificial Intelligence
Artificial Intelligence notes
10 chapter notes, in syllabus order. Each starts with the key points.
Unit 1
AI Basics: Definitions, History, Fields, Agents & EthicsUnit 1 of Artificial Intelligence introduces core concepts—what AI is, its history, key subfields, intelligent agents, and ethical considerations—with real-world examples from Nepalese apps and global tech giants.7 min readUnit 2
Intelligent Agents: Types, Environments & RationalityUnit 2 of Artificial Intelligence explores intelligent agents—autonomous entities that perceive and act in environments—covering agent types (reflex, model-based, goal-based), environment characteristics (accessible, deterministic, episodic), and rationality principles with worked examples from real-world systems like 9 min readUnit 3
Search Algorithms: Trees, States, and Optimal PathsUnit 3 of Artificial Intelligence explores systematic problem-solving techniques using search algorithms—how agents explore state spaces, game trees, and graphs to find solutions efficiently, with visual traces of explored paths, costs, and optimizations.14 min readUnit 4
Informed Search & Game Trees: Heuristics, A, Minimax, Alpha-BetaUnit 4 of Artificial Intelligence explores how to solve complex problems efficiently using heuristics (like A search) and optimal strategies in games (like Minimax and Alpha-Beta pruning), with real-world applications in route planning, decision-making, and competitive AI.10 min readUnit 5
Knowledge Representation & Logic: Facts, Rules & ReasoningUnit 5 of Artificial Intelligence covers how to encode real-world knowledge as data structures (propositional, predicate, frame logic) and use logical inference (forward/backward chaining) to derive new facts—critical for expert systems, NLP, and automated reasoning.12 min readUnit 6
Reasoning under Uncertainty: Probability, Bayes, Dempster-Shafer, and Decision TreesUnit 6 of Artificial Intelligence covers probabilistic reasoning, Bayesian networks, Dempster-Shafer theory, and decision-making under uncertainty, with real-world applications in medical diagnosis, fraud detection, and autonomous systems.9 min readUnit 7
Machine Learning Basics: Models, Algorithms & EvaluationUnit 7 of Artificial Intelligence covers supervised/unsupervised learning, regression/classification, model evaluation metrics (accuracy, precision, recall), bias-variance tradeoff, and real-world ML pipelines—with visuals, worked examples (e.g., predicting Daraz delivery delays), and exam-focused tips.7 min readUnit 8
Neural Networks: Architectures, Learning & ApplicationsUnit 8 of Artificial Intelligence explores neural networks—how they mimic human brain neurons, process data through layers, and learn via backpropagation. Covers architectures (feedforward, CNN, RNN), activation functions, loss metrics, and real-world deployments like recommendation systems and autonomous vehicles.13 min readUnit 9
NLP: Text Processing, ML Models & ApplicationsUnit 9 of Artificial Intelligence explores Natural Language Processing (NLP), covering text preprocessing, machine learning models (e.g., word embeddings, transformers), and real-world applications like chatbots, sentiment analysis, and machine translation.16 min readUnit 10
Expert Systems & AI Applications: Rules, Shells, and Real-World ImpactUnit 10 of Artificial Intelligence explores expert systems—how rule-based reasoning mimics human expertise in domains like medicine or finance—and their real-world applications in Nepal (e.g., Ncell’s fraud detection) and globally (e.g., IBM Watson). Covers forward/backward chaining, blackboard architecture, and AI’s s6 min read