Syllabus
- Biological inspiration in the design of algorithms and models
Evolutionary models
Neural models
- Evolutionary algorithms
Simple genetic algorithm
Representation, genetic operators, fitness, selection
Evolutionary algorithms for continuous optimization
Neuro-evolution, algorithm NEAT
Genetic programming
- Swarm algorithms
Ant Colony Optimization
Particle Swarm Optimization
- Neural networks
Perceptron, multi-layered perceptron, back-propagation as a learning algorithm
Convolutional networks
RBF networks a Kohonen’s maps
- Other nature inspired algorithms
Artificial Immune Systems
Cellular Automata
Artificial Life
- Applications in optimization and machine learning
Continuous and combinatorial optimization
Multi-objective optimization
Supervised and unsupervised learning, reinforcement learning
Annotation
The goal of the lecture is to introduce the main nature-inspired algorithms (evolutionary algorithm, neural networks, …) and how they can be applied to solve problems in optimization and machine learning. In the seminar, some of the algorithms will be implemented and used to solve simple problems in the areas mentioned above.