392124 Evolutionary Optimization and Learning (V) (SoSe 2022)

Title: Evolutionary Optimization and Learning
Table of Contents
• Introduction to optimization
- Definitions of optimization
- Types of optimization problems
- Multi-objective optimization
- Classical optimization algorithms
• Evolutionary algorithms
- Genetic algorithms
- Evolution strategies
- Genetic programming
• Swarm intelligence
- Particle swarm optimization
- Competitive swarm optimization
- Social learning swarm optimization
• Multi-objective evolutionary optimization
- Traditional methods
- Pareto based methods
- Decomposition based methods
- Performance indicator based methods
• Memetic algorithms
- Evolution and learning
- Baldwin effect versus hiding effect
- Baldwinian and Lamarkian mechanisms
• Data-driven evolutionary optimization
- Data-driven optimization and surrogate-assisted evolutionary optimization
- Model management strategies
- Bayesian evolutionary optimization
- Multi-objective data-driven evolutionary optimization
• Evolutionary learning
- Singe- and multi-objective evolutionary learning
- Evolutionary parameter and structure optimization of neural networks
- Evolutionary deep neural architecture search
- Evolutionary federated neural architecture search
- Privacy-preserving machine learning and federated learning
- Communication efficient federated learning
- Federated evolutionary neural architecture search

Requirements for participation, required level

Empfohlene Vorkenntnisse:

• machine learning
• neural networks

Bibliography

1. Jin, Y., Wang, H. and Sun, C. Data-Driven Evolutionary Optimization. Springer. 2021
2. Engelbrecht, A.P. Computational Intelligence – An Introduction. 2007
3. Snyman, J.A. Practical Mathematical Optimization: An Introduction to Basic Optimization Theory and Classical and New Gradient-Based Algorithms. Springer Publishing, 2005