A novel population initialization method for accelerating evolutionary algorithms

By Shahryar Rahnamayan, Hamid R. Tizhoosh, Magdy M. A. Salama. Computers and Mathematics with Applications, 2007

375 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/2ab2624511d48ecde46e80c9ca4f5bd94fbd0fdf

How researchers see this paper

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

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Opposition versus randomness in soft computing techniques (2008, background): “In a very short time, it was applied to enhance reinforcement learning [4–6,8,18,34], differential evolution [10–14], backpropagation neural networks [15,17], simulated annealing [9], ant colony optimization [16], and window memorization for morphological algorithms [7].”
Metaheuristics in large-scale global continues optimization: A survey (2015, methodology): “[148,146,145,147] enhanced DE (ODE) by using the concept of Opposition-Based Learning (OBL) which was proposed by Tizhoosh [170].”
A Multi-Facet Survey on Memetic Computation (2011, methodology): “Reference [83] proposed the opposition-based learning to initialize the foremost population, and showed that in contrast to random initialization, their proposed population initialization method helped to accelerate the search convergence rate.”
Toward an optimal kernel extreme learning machine using a chaotic moth-flame optimization strategy with applications in medical diagnoses (2017, background): “Having good initial population positions ensures fast convergence and a good final solution for swarm intelligence optimization algorithms [38, 39].”
A literature survey of benchmark functions for global optimisation problems (2013, neutral): “ Multimodal) f 154(x) = 1 + XD i=1 8sin2 7(xi −0.9)2 +6sin2 14(x 1 −0.9)2 +(xi −0.9)2 subject to −500 ≤ xi ≤ 500. The global minimum is located at x∗ = f(0.9,··· ,0.9), f(x∗) = 1 155. Tripod Function [69](Discontinuous, Non-Diﬀerentiable, Non-Separable, Non-Scalable, Multimodal) f 155(x) = p(x 2)(1 ”
On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice (2020, methodology): “To generate hyper-parameter configuration candidates for the initial population, random initialization that simply creates the initial population with random values in the given search space is often used in GA [101].”
Opposition-Based Differential Evolution (2008, background): “• A general scheme of opposition-based population initialization is proposed to accelerate evolutionary algorithms [Rahnamayan et al. 2006b; Rahnamayan 2006].”