H.A. Abbass, R. Sarker, and C. Newton. A pareto di#erential evolution approach to vector optimisation problems. IEEE Congress on Evolutionary Computation, IEEE Publishing, Seoul, Korea, 2:971--978, 2001. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
An Evolutionary Artificial Neural Networks Approach for Breast.. - Abbass (2002) (1 citation) Self-citation (Abbass) (Correct)
....between the network architecture and weights. The objective of the proposed method in this paper is to train and determine the number of hidden units in the network simultaneously. Thus, in the following section, the proposed method is introduced. 2. 4 Pareto Di#erential Evolution Abbass et al. [1] described the Pareto frontier Di#erential Evolution (PDE) algorithm for vector optimization problems. The algorithm is an adaptation of the original Di#erential evolution (DE) introduced by Storn and Price [30] for optimization problems over continuous domains. The PDE method outperformed all ....
....solution from the population and finding the pareto optimal solutions in the remainder of the population. Those solutions dominating the rest of the population are added to the pareto set until the number of pareto solutions in the set is 3. Our proposed method amalgamates the original PDE [1] algorithm with local search (i.e. BP) to form the memetic approach. In initial investigations, the algorithm was quite slow and the use of local search improved its performance. MPANN consists of the following steps: 12 1. Create a random initial population of potential solutions. The elements ....
[Article contains additional citation context not shown here]
H.A. Abbass, R. Sarker, and C. Newton. A pareto di#erential evolution approach to vector optimisation problems. IEEE Congress on Evolutionary Computation, IEEE Publishing, Seoul, Korea, 2:971--978, 2001.
A Memetic Pareto Evolutionary Approach to Artificial Neural.. - Abbass (2001) Self-citation (Abbass) (Correct)
....approaches, o#ers more flexibility. There has been a number of methods in the literature for population based non pareto [23] and pareto [9, 32, 13] approaches to MOPs. More recently, we developed the Pareto Di#erential Evolution (PDE) method using Di#erential Evolution (DE) for MOPs [1]. The PDE method outperformed all previous methods on five benchmark problems. 2.5 Evolutionary Artificial Neural Networks Over the last two decades, research into EANN has witnessed a flourish period [28, 27] Yao [29] presents a thorough review to the field with over 300 references just in the ....
....optimal solution from the population and finding the pareto optimal solutions in the remainder of the population. Those solutions dominating the rest of the population are added to the pareto list until the number of pareto solutions in the list is 3. Our proposed method augments the original PDE [1, 22] algorithm with local search (i.e. BP) to form the memetic approach. In initial investigations, the algorithm was quite slow and the use of local search improved its performance. MPANN consists of the following steps: 1. Create a random initial population of potential solutions. The elements of ....
[Article contains additional citation context not shown here]
H.A. Abbass, R. Sarker, and C. Newton. A pareto di#erential evolution approach to vector optimisation problems. Congress on Evolutionary Computation, 2:971--978, 2001.
The Self-Adaptive Pareto Differential Evolution - Abbass (2002) Self-citation (Abbass) (Correct)
....traditional approaches to MOPs. EMO methods do not have assumptions underlying the MOP. In addition, most of them are population based; therefore they can generate a number of pareto solutions in a single run. One of the recent approaches to EMO is the Pareto Di#erential Evolution (PDE) algorithm [1]. The algorithm was designed for EMO problems with continuous variables and achieved a very competitive results compared to other algorithms in the EMO literature. However, there was no obvious way to select the best crossover and mutation rates apart from running the algorithm with di#erent ....
....100 (a b) represents the percentage of the pareto frontier where both A and B are statistically insignificant at confidence level 0.95. III. Self adaptive Pareto Di#erential Evolution The SPDE algorithm for vector optimization problems is an adaptation of the PDE algorithm described in [1]. Similar to PDE, the SPDE algorithm works as follows. Assuming that all variables are bounded between [0,1] an initial population is generated at random from a Gaussian distribution with mean 0.5 and standard deviation 0.15. All dominated solutions are removed from the population. The remaining ....
[Article contains additional citation context not shown here]
H.A. Abbass, R. Sarkar, and C. Newton. A pareto di#erential evolution approach to vector optimisation problems. The IEEE Congress on Evolutionary Computation, Seoul, Korea, pages 971--978, 2001.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC