-
Chapter and Conference Paper
Saliency Can Be All You Need in Contrastive Self-supervised Learning
We propose an augmentation policy for Contrastive Self-Supervised Learning (SSL) in the form of an already established Salient Image Segmentation technique entitled Global Contrast based Salient Region Detecti...
-
Article
Multi-level evolution strategies for high-resolution black-box control
This paper introduces a multi-level (m-lev) mechanism into Evolution Strategies (ESs) in order to address a class of global optimization problems that could benefit from fine discretization of their decision v...
-
Chapter and Conference Paper
The Unreasonable Effectiveness of the Final Batch Normalization Layer
Early-stage disease indications are rarely recorded in real-world domains, such as Agriculture and Healthcare, and yet, their accurate identification is critical in that point of time. In this type of highly i...
-
Article
Christian Blum and Günther R. Raidl: Hybrid metaheuristics—powerful tools for optimization
-
Living Reference Work Entry In depth
Evolution Strategies
Evolution strategies are classical variants of evolutionary algorithms which are frequently used to heuristically solve optimization problems, in particular in continuous domains. In this chapter, a descriptio...
-
Reference Work Entry In depth
Evolution Strategies
Evolution strategies are classical variants of evolutionary algorithms which are frequently used to heuristically solve optimization problems, in particular in continuous domains. In this chapter, a descriptio...
-
Article
Searching for the Pareto frontier in multi-objective protein design
The goal of protein engineering and design is to identify sequences that adopt three-dimensional structures of desired function. Often, this is treated as a single-objective optimization problem, identifying t...
-
Chapter and Conference Paper
Pareto Landscapes Analyses via Graph-Based Modeling for Interactive Decision-Making
We consider two complementary tasks for consuming optimization results of a given multiobjective problem by decision-makers. The underpinning in both exploratory tasks is analyzing Pareto landscapes, and we pr...
-
Article
Quantum control experiments as a testbed for evolutionary multi-objective algorithms
Experimental multi-objective Quantum Control is an emerging topic within the broad physics and chemistry applications domain of controlling quantum phenomena. This realm offers cutting edge ultrafast laser lab...
-
Reference Work Entry In depth
Niching in Evolutionary Algorithms
Niching techniques are the extension of standard evolutionary algorithms (EAs) to multi-modal domains, in scenarios where the location of multiple optima is targeted and where EAs tend to lose population diver...
-
Chapter and Conference Paper
A Reduced-Cost SMS-EMOA Using Kriging, Self-Adaptation, and Parallelization
The SMS-EMOA is a simple and powerful evolutionary metaheuristic for computing approximations to Pareto front based on the dominated hypervolume indicator (S-metric). However, as other state-of-the-art metaheu...
-
Article
Niching with derandomized evolution strategies in artificial and real-world landscapes
We introduce a framework of derandomized evolution strategies (ES) niching techniques. A survey of these techniques, based on 5 variants of derandomized ES, is presented, based on the fixed niche radius approach....
-
Chapter and Conference Paper
Enhancing Decision Space Diversity in Evolutionary Multiobjective Algorithms
In multi-criterion optimization, Pareto-optimal solutions that appear very similar in the objective space may have very different pre-images. In many practical applications the decision makers, who select a so...
-
Chapter
Niching Methods: Speciation Theory Applied for Multi-modal Function Optimization
While contemporary Evolutionary Algorithms (EAs) excel in various types of optimizations, their generalization to speciational subpopulations is much needed upon their deployment to multi-modal landscapes, mai...
-
Chapter and Conference Paper
Mixed-Integer Evolution Strategies with Dynamic Niching
Mixed-Integer Evolution Strategies (MIES) are a natural extension of standard Evolution Strategies (ES) for addressing optimization of various types of variables – continuous, ordinal integer, and nominal disc...
-
Chapter and Conference Paper
Niche Radius Adaptation with Asymmetric Sharing
In the field of Genetic Algorithms, niching techniques have been invented with the aim to induce speciation on multimodal fitness landscapes. Unfortunately, they often rely on a problem-dependent niche radius par...
-
Chapter and Conference Paper
Gaining Insights into Laser Pulse Sha** by Evolution Strategies
We consider the numerical evolutionary optimization of dynamic molecular alignment by shaped femtosecond laser pulses. We study a simplified model of this quantum control problem, which allows the full physical i...
-
Chapter and Conference Paper
Classification of Cell Fates with Support Vector Machine Learning
In human mesenchymal stem cells the envelope surrounding the nucleus, as visualized by the nuclear lamina, has a round and flat shape. The lamina structure is considerably deformed after activation of cell dea...
-
Chapter and Conference Paper
Learning the Complete-Basis-Functions Parameterization for the Optimization of Dynamic Molecular Alignment by ES
This study further investigates the complete-basis-functions parameterization method (CBFP) for Evolution Strategies (ES), and its application to a challenging real-life high-dimensional physics optimization prob...
-
Chapter and Conference Paper
Niching in Evolution Strategies and Its Application to Laser Pulse Sha**
Evolutionary Algorithms (EAs), popular search methods for optimization problems, are known for successful and fast location of single optimal solutions. However, many complex search problems require the locati...
