Evolutionary algorithms in theory and practice - evolution strategies, evolutionary programming, genetic algorithms

By Thomas Bäck. 1996

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Surrogate-Assisted Evolutionary Deep Learning Using an End-to-End Random Forest-Based Performance Predictor (2020, methodology): “This will become even more severe in the case of a large population and with a large number of generations, which is a more widely used configuration of evolutionary algorithms targeting at finding the better solutions [16], [18], [27].”
Overcoming Multi-Model Forgetting (2019, neutral): “By contrast, neuro-evolution strategies use evolutionary algorithms (B¨ack, 1996) to perform the search.”
A survey and critique of multiagent deep reinforcement learning (2018, methodology): “, evolutionary methods [232, 233, 227, 228] or sampling-based methods, have shown good results [155, 176, 156].”
Software Architecture Optimization Methods: A Systematic Literature Review (2013, background): “Interestingly, Evolutionary Algorithms are less frequently validated than many other metaheuristics, although it is known that an evolutionary algorithm’s performance and quality of results can significantly vary for different optimization parameters and problem formulations [19], [20], [225].”
Surrogate-Assisted Learning of Neural Networks (2017, background): “Evolutionary algorithms [1] are based on the principles of natural selection: in each generation, a population of individuals (e.g. solutions ˛ w ) is evolved by mutation, recombination and selection steps.”
PUF Modeling Attacks on Simulated and Silicon Data (2013, background): “2) Evolution Strategies: Evolution Strategies (ES) [1], [39] belong to an ML subfield known as population-based heuristics.”
Guided GUI testing of android apps with minimal restart and approximate learning (2013, methodology): “Evolutionary algorithms [14,127] have been used to test programs [102].”
A phylogenetic, ontogenetic, and epigenetic view of bio-inspired hardware systems (1997, background): “…BIOLOGICAL INSPIRATION AS A BRIDGE FROM THE NATURAL SCIENCES TOENGINEERING T RADITIONALLY, the development of the engineeringdisciplines (civil, electrical, computer engineering, etc.) and that of the natural sciences (physics, chemistry, biology, etc.) have proceeded along separate tracks.”
Aerodynamic Shape Optimization Using First and Second Order Adjoint and Direct Approaches (2008, methodology): “The design of optimally shaped aerodynamic configurations based on an available analysis software (flow solver) and predefined targets (objective functions) can be solved using stochastic [3–6] or deterministic [7–11] search algorithms, without excluding any hybridization of them.”
Salp Swarm Algorithm: A bio-inspired optimizer for engineering design problems (2017, methodology): “20 Meta-heuristic algorithms are classified into two dominant lasses: evolutionary [1] and swarm intelligence [2] techniques.”