Artificial Intelligence Engineering
Comprehensive academic and industrial engineering curriculum covering rational agents, state-space heuristic search, adversarial game trees, constraint satisfaction, probabilistic reasoning, knowledge representation ontologies, and autonomous cognitive systems.
Introduction to Artificial Intelligence
Historical evolution from the 1950 Turing Test and 1956 Dartmouth workshop, ANI vs AGI vs ASI taxonomies, the four foundational approaches to intelligence, state space problem formulation, and modern Python AI workstation setup.
Intelligent Agents
The perception-action cycle, agent functions vs programs, the 5 core agent architectures (Reflex, Model-Based, Goal-Based, Utility-Based, Learning), task environment taxonomies, and PEAS formulation.
Problem Solving & Search
State-space graph search, BFS, DFS, DLS, Iterative Deepening, Uniform-Cost Search, heuristic A* admissibility and consistency, local search optimization (Hill Climbing, Simulated Annealing, GAs), and Constraint Satisfaction Problems (CSPs).
Game Playing & Adversarial Search
Two-player zero-sum games, game trees, the Minimax decision rule, Alpha-Beta pruning with move ordering, heuristic evaluation functions with quiescence search, Expectimax for stochastic games, and Monte Carlo Tree Search (MCTS) foundations.
Knowledge Representation & Reasoning
Knowledge-based agent architecture (TELL/ASK), propositional logic truth tables and resolution refutation, First-Order Logic (FOL) with unification, forward and backward chaining on Horn clauses, semantic networks, frames, ontologies, and Description Logics.
Automated Planning & Acting
Factored state-action spaces in STRIPS and PDDL, forward progression vs. backward regression, Partial-Order Planning (POP) with causal links, Planning Graphs with mutex relationships, GRAPHPLAN, and Hierarchical Task Networks (HTN).
Uncertain Knowledge & Reasoning
Probability foundations, Bayes' Theorem, Bayesian Networks with exact and approximate sampling, temporal models (Hidden Markov Models, Viterbi decoding), Markov Decision Processes (MDPs) with Bellman equations, and Decision Theory.
Machine Learning Foundations
Supervised, unsupervised, semi-supervised, and reinforcement learning paradigms, preprocessing pipelines, Decision Trees, Naive Bayes, KNN, Support Vector Machines (SVM), K-Means clustering, cross-validation, and the Bias-Variance tradeoff.
Neural Networks & Deep Learning
Biological vs artificial neurons, the Rosenblatt Perceptron and XOR barrier, activation functions, Universal Approximation Theorem, Backpropagation calculus, PyTorch vs TensorFlow, CNNs, RNNs, LSTMs, and Transformer self-attention.
Natural Language Processing
Computational linguistics pipeline, tokenization, stemming vs lemmatization, POS tagging, Named Entity Recognition, TF-IDF vectors, Word2Vec embeddings, neural translation, Large Language Models (LLMs), and prompt engineering architectures.
Computer Vision & Visual Perception
Digital image representations, spatial filtering, Sobel and Canny edge detectors, Harris corners, SIFT/HOG descriptors, object detection pipelines (R-CNN, YOLO), image segmentation, FaceNet face verification, and transfer learning.
Expert Systems & Knowledge Engineering
Foundations of symbolic AI, production rule systems, inference engines (Match-Resolve-Act cycle & Rete), Forward and Backward Chaining, explanation facilities (Why & How audits), and clinical/financial applications.
Robotics & Autonomous Systems
Physical embodiment of AI, proprioceptive and exteroceptive sensors, SLAM localization and mapping, A* and RRT* path planning, kinematics, SAE Levels 0–5 autonomous vehicles, and collaborative cobots.
Reinforcement Learning & Control
Sequential decision making, Markov Decision Processes (MDPs), Bellman equations, exploration vs exploitation, tabular Q-Learning, Deep Q-Networks (DQN), and applications in gaming, robotics, and LLM RLHF alignment.
Generative AI & Agentic Systems
Foundations of generative modeling, GANs, VAEs, Diffusion models, text-to-image synthesis, Transformers, Large Language Models (LLMs), prompt engineering, Retrieval-Augmented Generation (RAG), and autonomous ReAct tool agents.