I will reply and close issues on this repository after the exam is done, thank you for the comments and suggestions.
The course introduces various computational methods and data processing that can be labeled "artificial intelligence".
In more details students will:
- gain expertise on top-down and bottom-up methods where solutions are searched or built through trial-and-error
- acquire knowledge on approximate optimization techniques and exploit the relationship between optimization and learning
- understand the concepts of path-, local-, and policy-search
- learn how to tackle problems involving highly-structured, uncertain (possible), and imprecise (fuzzy) information
The course also encompasses general multi-agent systems and a range of algorithms inspired by natural systems, such as genetic algorithms, genetic programming, and swarm optimization. The lectures will cover theoretical foundations, algorithm design, implementation, and applications to real-world problems.
Introduction
- What is "Computational Intelligence"? (included: what is "Artificial Intelligence"? Weak AI vs. Strong AI; the Turing Test; ...)
- Symbolic vs. Sub-symbolic intelligence
- Solving problems by searching; trial n'error vs. learning vs. evolution
- Metaheuristics (exact vs. approximate, ad-hoc heuristics)
- Evolutionary Computation (bio-inspired methodologies, natural selection)
Single-State Methods
- Hill-climbing, simulated annealing, iterated local search, variable neighborhood search
- Simple Evolution Strategies: (1+1), (1+λ) and (1,λ)
Population Methods
- Unified approach to Evolutionary Algorithms
- Parameter optimization (Evolution Strategies, Differential Evolution)
- Symbolic regression (Genetic Programming)
- Swarm intelligence (Ant Colony Optimization, Particle Swarm Optimization)
- Memetic Algorithms (hybridization)
- Model fitting (Estimation of Distribution Algorithm)
- Multi-objective optimization
Representation problems; genotype space and operators
- Knowledge representation
- Trivial (bit strings, integer, real numbers); Permutations; Graphs
- Fuzzification
Policy optimization
- Reinforcement learning, Q-Learning (not included: Deep Q-Learning)
- Rule-based systems and Learning Classifier Systems
Multi agent systems
- Artificial Immune System and Learning Classifier System
- Simple agents
- Learning agents
- Games (Adversarial Search)