Nature Inspired AI

Recommended Prerequisites

Introduction to Programming and Problem solving, Introduction to Artificial Intelligence, Statistics. Reading and writing English skills.

Teaching Methods

In the theoretical classes we will present and discuss in a critical way the theories and methods used in heuristic problem solving. In the pratical classes students will exercise what was taught by solving in the computer medium complexity problems. This is a group work done under the supervision of the professor. Written synthesis of a recent research work, experimental work involving the statistical study of different alternatives for a theoretical question. Work subject to oral presentation and discussion.

Learning Outcomes

Present, discuss and develop computational methods for naturally inspired artificial intelligence solutions (i.e., biological, social, physical) for highly complex problems that either have no analytical solution or are computationally intractable.

Acquisition of skills to rigorously evaluate alternative solutions to problems.

Acquisition of skills in analysis and synthesis, oral and written communication (Portuguese and English), computer skills and statistical analysis, problem solving, knowledge of a foreign language, critical thinking, group work, autonomous learning, creativity, practical application of knowledge, research.

Work Placement(s)

No

Syllabus

1. Introduction
2. Classic Meta-Heuristics
a. Random Search
b. Hill Climbers
c. Simulated Annealing
3. Generic Evolutionary Algorithms
4. Genetic Algorithms
a. Binary
b. Real-Number
c. Permutations
5. Genetic Programming
a. Tree-Based
b. Graph-based
c. Linear
d. Grammar-based
6. Evolutionary Strategies
a. Classical
b. CMA-ES
c. Natural ES
7. Differential Evolution
8. Co-Evolution
a. Co-operation
b. Competition
9. Multi-Objective Optimization
a. MOEAs
10. Evolutionary Machine Learning
a. EC as Machine Learning
b. EC for Machine Learning
c. Neuroevolution
11. Collective Intelligence
a. Ant Colony Optimization
b. Particle Swarm Optimization
12. Design of Experiments and Evaluation.

Head Lecturer(s)

Nuno António Marques Lourenço

Assessment Methods

Assessment
Synthesis work: 10.0%
Project: 30.0%
Exam: 60.0%

Bibliography

Handbook of Evolutionary Machine Learning. Wolfgang Banzhaf, Penousal Machado, and Mengjie Zhang,  Springer, 2023.

-Lectures on Intelligent Systems, Leonardo Vanneschi, Sara Silva, Springer, 2023

-Introduction to Evolutionary Computation (2nd edition), A. Eiben and J. Smith, Springer, 2015.

-Natural Computing Algorithms, Anthony Brabazon, Michael O’Neill and Seán McGarraghy, Springer, 2015.

-Bio-Inspired Artificial Intelligence: theories, methods, and Technologies, Dario Floreano and Claudio Mattiussi, MIT Press, 2008

-Evolutionary Deep Learning: Genetic algorithms and neural networks, Micheal Kanham, Manning, 2023

-Genetic Algorithms and Machine Learning for Programmers: Create AI Models and Evolve Solutions, Frances Buontempo, Pragmatic Bookshelf, 2019.