The electromagnetism-like(EM)algorithm is a meta-heuristic optimization algorithm,which uses a novel searching mechanism called attraction-repulsion between charged particles.It is worth pointing out that there are tw...The electromagnetism-like(EM)algorithm is a meta-heuristic optimization algorithm,which uses a novel searching mechanism called attraction-repulsion between charged particles.It is worth pointing out that there are two potential problems in the calculation of particle charge by the original EM algorithm.One of the problems is that the information utilization rate of the population is not high,and the other problem is the decline of population diversity when the population size is much greater than the dimension of the problem.In contrast,it is more fully to exploit the useful search information based on the proposed new quadratic formula for charge calculation in this paper.Furthermore,the population size was introduced as a new multiplier term to improve the population diversity.In the end,numerical experiments were used to verify the performance of the proposed method,including a comparison with the original EM algorithm and other well-known methods such as artificial bee colony(ABC),and particle swarm optimization(PSO).The results showed the effectiveness of the proposed algorithm.展开更多
Boundary equilibrium generative adversarial networks(BEGANs)are the improved version of generative adversarial networks(GANs).In this paper,an improved BEGAN with a skip-connection technique in the generator and the d...Boundary equilibrium generative adversarial networks(BEGANs)are the improved version of generative adversarial networks(GANs).In this paper,an improved BEGAN with a skip-connection technique in the generator and the discriminator is proposed.Moreover,an alternative time-scale update rule is adopted to balance the learning rate of the generator and the discriminator.Finally,the performance of the proposed method is quantitatively evaluated by Fréchet inception distance(FID)and inception score(IS).The test results show that the performance of the proposed method is better than that of the original BEGAN.展开更多
基金National Natural Science Foundation of China(Nos.61602398 and U19A2083)Science and Technology Development of Hunan Province,China(No.2019GK4007)。
文摘The electromagnetism-like(EM)algorithm is a meta-heuristic optimization algorithm,which uses a novel searching mechanism called attraction-repulsion between charged particles.It is worth pointing out that there are two potential problems in the calculation of particle charge by the original EM algorithm.One of the problems is that the information utilization rate of the population is not high,and the other problem is the decline of population diversity when the population size is much greater than the dimension of the problem.In contrast,it is more fully to exploit the useful search information based on the proposed new quadratic formula for charge calculation in this paper.Furthermore,the population size was introduced as a new multiplier term to improve the population diversity.In the end,numerical experiments were used to verify the performance of the proposed method,including a comparison with the original EM algorithm and other well-known methods such as artificial bee colony(ABC),and particle swarm optimization(PSO).The results showed the effectiveness of the proposed algorithm.
基金National Natural Science Foundation of China(Nos.61602398,U19A2083)Science and Technology Department of Hunan Province,China(No.2019GK4007)。
文摘Boundary equilibrium generative adversarial networks(BEGANs)are the improved version of generative adversarial networks(GANs).In this paper,an improved BEGAN with a skip-connection technique in the generator and the discriminator is proposed.Moreover,an alternative time-scale update rule is adopted to balance the learning rate of the generator and the discriminator.Finally,the performance of the proposed method is quantitatively evaluated by Fréchet inception distance(FID)and inception score(IS).The test results show that the performance of the proposed method is better than that of the original BEGAN.
