Artificial Intelligence syllabus

Artificial Intelligence

• 1 Introduction (3 LHs)

  • Intelligence and AI perspectives, history and foundations
  • AI ethics: bias, fairness, transparency and accountability
  • AI regulation, policy and applications
• 2 Intelligent Agents (4 LHs)

  • Agent structure, properties, PEAS and PAGE
  • Reflex, model-, goal-, utility- and learning agents
  • Deterministic/stochastic, static/dynamic and observable environments
• 3 Problem Solving by Searching (9 LHs)

  • State spaces and problem formulation
  • Uninformed search: DFS, BFS, depth-limited, iterative and bidirectional
  • Informed search: greedy and A*
  • Hill climbing and simulated annealing
  • Adversarial search, minimax and alpha-beta pruning
  • Constraint-satisfaction problems
• 4 Knowledge Representation (14 LHs.)

  • Semantic nets, frames, scripts, conceptual dependencies and rules
  • Propositional logic syntax, semantics and inference
  • Predicate logic, quantification, unification and resolution
  • Forward and backward chaining
  • Uncertainty, Bayes' rule and Bayesian networks
  • Fuzzy sets and fuzzy rule systems
• 5 Machine Learning (12 LHs)

  • Supervised, unsupervised and reinforcement learning
  • Naive Bayes
  • Genetic algorithms: selection, crossover, mutation and fitness
  • Artificial neural networks and activation functions
  • Hebbian, perceptron and back-propagation learning
  • CNNs, RNNs and GANs
• 6 Applications of AI (6 LHs)

  • Expert systems and components
  • Natural language processing and machine translation
  • Computer vision, recognition and image segmentation
  • Explainable AI in vision
  • AI in healthcare and bioinformatics
• 7 Laboratory Works

  • Intelligent agents, knowledge representation and machine learning programs
  • Neural networks for practical AI problems
  • LISP, PROLOG or a suitable high-level language