• Bio-inspired computation: problem representation, emulation of biological principles. Candidate solutions, fitness, and survival of the fittest. Exploration and exploitation.
• Trajectory and population-based methods, families of bio-inspired methods: evolutionary computation, swarm intelligence, artificial neural networks.
• Evolutionary computation: basic principles (population, selection, elimination, ...), genetic algorithms, genetic programming, differential evolution.
• Swarm intelligence: basic principles (social intelligence), particle swarm optimization, ant colony optimization, artificial bee colony optimization.
• Artificial neural networks: artificial neuron, multilayer networks, deep networks. Supervised and unsupervised learning, deep learning.
• Continuous problems, parameter learning, benchmarking functions.
• Combinatorial optimization problems, permutation (travelling salesman problem) and subset selection problems (feature subset selection).
• Statistical analysis, evaluation, and visualization of bio-inspired methods.
• Trajectory and population-based methods, families of bio-inspired methods: evolutionary computation, swarm intelligence, artificial neural networks.
• Evolutionary computation: basic principles (population, selection, elimination, ...), genetic algorithms, genetic programming, differential evolution.
• Swarm intelligence: basic principles (social intelligence), particle swarm optimization, ant colony optimization, artificial bee colony optimization.
• Artificial neural networks: artificial neuron, multilayer networks, deep networks. Supervised and unsupervised learning, deep learning.
• Continuous problems, parameter learning, benchmarking functions.
• Combinatorial optimization problems, permutation (travelling salesman problem) and subset selection problems (feature subset selection).
• Statistical analysis, evaluation, and visualization of bio-inspired methods.