Genetic Algorithms in Search Optimization and Machine Learning

By David E. Goldberg. 1988

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

Deep learning in neural networks: An overview (2014, background): “RL NNs can also be evolved through Evolutionary Algorithms (EAs) (Rechenberg, 1971; Schwefel, 1974; Holland, 1975; Fogel et al., 1966; Goldberg, 1989) in a series of trials.”
Reinforcement Learning: A Survey (1996, background): “Classi er Systems Classi er systems (Holland, 1975; Goldberg, 1989) were explicitly developed to solve problems with delayed reward, including those requiring short-term memory.”
Learning Simple Algorithms from Examples (2015, neutral): “Genetic algorithms [Holland (1992); Goldberg (1989)] also can be considered a form of program induction, but are mostly based on a random search strategy rather than a learned one.”
NSGA-NET: A Multi-Objective Genetic Algorithm for Neural Architecture Search (2018, background): “However, optimizing with N population members processes O ( N 3 ) sub-regions of the search space in parallel Goldberg (1989); Holland (1975).”
On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models (2015, methodology): “1, except that C is now an FNN or RNN trained by evolutionary algorithms [200, 255, 105, 56, 68] applied to NNs [165, 321, 180, 259, 72, 90, 89, 110, 94], or by policy gradient methods [314, 315, 316, 274, 18, 1, 63, 128, 313, 210, 192, 191, 256, 85, 312, 190, 82, 93][245, Sec.”
TREATING CONSTRAINTS AS OBJECTIVES FOR SINGLE-OBJECTIVE EVOLUTIONARY OPTIMIZATION (2000, methodology): “1 INTRODUCTION Even when genetic algorithms (GAs) have been quite successful in a wide range of applications [1, 2], their use in constrained optimization problems raises several issues to which a considerable amount of research has been devoted in the last few years.”
Smart Pareto filter: obtaining a minimal representation of multiobjective design space (2004, methodology): “Goldberg [17] developed a Pareto-genetic algorithm that uses a Pareto ranking procedure to move a population toward the Pareto frontier.”
Genetic Fuzzy Systems - Evolutionary Tuning and Learning of Fuzzy Knowledge Bases (2002, methodology): “These concepts were introduced in GAs in order to improve their behaviour when dealing with multimodal functions with peaks of unequal value (Deb and Goldberg, 1989; Goldberg, 1989).”
A novel hysteretic model for magnetorheological fluid dampers and parameter identification using particle swarm optimization (2006, background): “, genetic algorithms [13], [14], have also been widely applied in modelling and parameter identification applications and many others.”
Three Scheduling Algorithms Applied to the Earth Observing Systems Domain (2000, methodology): “A more popular approach is the roulette wheel method (Goldberg 1989), in which case the population members are given a probability of selection in proportion to the percent of the total score that they represent.”
A Survey of Evolutionary Algorithms for Clustering (2009, methodology): “In brief, the author seriously questioned the applicability of the schema theorem [54], [63] for”
On measuring multiobjective evolutionary algorithm performance (2000, methodology): “Only one citation in the known literature (Van Veldhuizen , 1999) reports any quantitative results concerning the number of \waves" or fronts produced (per generation) by implementing Goldberg's Pareto ranking scheme.”