Search

An optimization spiking neural P (OSN P) system is a discrete optimization model without the aid of evolutionary operators of evolutionary algorithms or swarm intelligence algorithms. However, since the processing object of OSN P systems is a spike, where information is encoded by the timing of spikes or the number of spikes in neurons, OSN P systems are limited for solving continuous optimization problems. To break this limitation, an extended numerical spiking neural (ENSN P) system is proposed based on numerical spiking neural P (NSN P) systems and multiple (ENSN P) systems, called optimization numerical spiking neural P systems (ONSN P systems or ONSNPS), are designed to solve continuous constrained optimization problems. More specifically, in ENSN P systems, the production functions are selected by probability to achieve updated parameters. In OSN P systems, a guider algorithm is introduced to finish individuals' crossover and selection. The extensively experimental results in five benchmarks, thirty-two optimization problems including five benchmark problems, seventeen manufacturing design optimization problems and ten benchmarks from CEC show that ONSN P systems in this paper outperform or are competitive to twenty-eight optimization algorithms. Finally, algorithm complexity and Holm-Bonferroni procedure based on statistical results is used to test the complexity changing when we use different dimensionality of the search space and the difference in terms of statistical performance. The testing results indicate that the time complexity of ONSN P systems grows linearly with problem dimensions and ONSN P systems are better performance than the most algorithms. [ABSTRACT FROM AUTHOR]

Network pruning has been a hot topic in recent years, and many popular pruning methods rely on network design expertise. However, the pruning process usually involves manual intervention and can be difficult for users who lack prior knowledge. Automatic pruning using evolutionary algorithms shows great promise, but it must address the challenge of performing time-consuming model evaluations and searching through a large solution space. Dataset distillation is a technique that compresses the original dataset to decrease the cost of fine-tuning models. In this paper, we explore the potential of using the distilled dataset to exhibit a similar role as the real dataset in network pruning, and proposed the evolutionary pruning framework using distilled dataset. Specifically, the network pruning pipeline is carried out on the distilled dataset to significantly reduce the model evaluation cost, and the number of filters in the convolutional layer is directly coded to narrow the search space. In addition, a tailored evolutionary algorithm is proposed that takes the form of constrained optimization to search the most suitable pruned network. The experiments conducted on VGG16, VGG19, ResNet56, and ResNet110 demonstrate that the proposed method reduces at least 41.56% of the flops and achieves competitive results with little compromising accuracy. • Distillation dataset is first applied to network pruning. • A constrained evolutionary algorithm with double-balanced multi-branch is proposed. • Deep convolutional neural network pruning is performed using the constrained evolutionary algorithm. [ABSTRACT FROM AUTHOR]

Constrained multi-objective optimization problems (CMOPs) are difficult to handle because objectives and constraints need to be considered simultaneously, especially when the constraints are extremely complex. Some recent algorithms work well when dealing with CMOPs with a simple feasible region; however, the effectiveness of most algorithms degrades considerably for CMOPs with complex feasible regions. To address this issue, this paper proposes a multi-stage evolutionary algorithm, where constraints are added one after the other and handled in different stages of evolution. Specifically, in the early stages, the algorithm only considers a small number of constraints, which can make the population efficiently converge to the potential feasible region with good diversity. As the algorithm moves to the later stages, more constraints are considered to search the optimal solutions based on the solutions obtained in the previous stages. Furthermore, a strategy for sorting the constraint-handling priority according to the impact on the unconstrained Pareto front is proposed, which can accelerate the convergence of the algorithm. Experimental results on five benchmark suites and three real-world applications showed that the proposed algorithm outperforms several state-of-the-art constraint multi-objective evolutionary algorithms when dealing with CMOPs, especially for problems with complex constraints. [ABSTRACT FROM AUTHOR]

It is of necessity to select appropriate optimization algorithms from an algorithm library due to the universality of constrained multi-objective optimization problems and the suitability of intelligent optimization algorithms, which requires a rich optimization algorithm library. This paper proposes a migration-based method of enriching the algorithm library for constrained multi-objective optimization problems. After calculating the similarity between problems based on their landscape features, the proposed method calculates the migration probabilities of intelligent optimization algorithms solving similar problems based on the performance of each algorithm and the similarity between problems. According to the redundancy and compatibility of components, the algorithms with large migration probabilities enrich the algorithm library for solving the current problem. Based on the enhanced algorithm library, a Softmax regression model is trained to generate an optimal intelligent algorithm to solve the current problem. The proposed method is applied to solve a series of constrained multi-objective optimization benchmark problems and the operation optimization problems of an integrated coal mine energy system, and the experimental results verify its effectiveness and feasibility. • A method based on landscape features is proposed to determine similar problems. • A method is given to select migrated algorithms based on similarity and performance. • A method based on redundancy and compatibility is presented to enrich an IOAL. [ABSTRACT FROM AUTHOR]

Constrained multi-objective optimization problems (CMOPs) are challenging due to the complexity of feasible regions caused by constraints, especially when facing small feasible ranges, multiple feasible regions, and complex distribution of feasible regions. Existing algorithms struggle to balance population convergence, diversity, and feasibility. This paper proposes a constrained multi-objective evolutionary algorithm framework based on global and local feasible solutions search to address this issue. The proposed framework is divided into three stages, and an adaptive method is proposed to decide when to switch the search state. In the first two stages, the evolution of the population is relatively free and not subject to constraint restrictions. Feasible solutions in the population are saved in the FeasiblePool for environmental selection during these two stages. The FeasiblePool does not affect the evolving population during these stages. In the first stage, the framework uses global search operator to fully explore the decision space and determine the rough range of feasible solutions in the decision space. In the second stage, the framework uses local search operator to enhance the diversity of FeasiblePool within this determined range. In the last stage, the framework reuses these excellent feasible solutions information to guide population evolution while considering constraints. The proposed framework has been compared with four state-of-the-art constrained multi-objective algorithms on four benchmark suites and three real-world applications. The complete experimental results show that the proposed framework has high competitiveness for solving CMOPs. [ABSTRACT FROM AUTHOR]

• A novel CHT is proposed based on Pareto dominance-based ranking and CDP-based ranking. • A search algorithm based on four mutation operators is proposed. • A new constrained multiobjective differential evolution algorithm is proposed. The tradeoff between objective functions and constraints is a key issue that needs to be addressed by constrained multiobjective optimization algorithms, and constraint handling techniques (CHTs) are an important technique for balancing objective functions and constraints. In this paper, a novel CHT that fuses two rankings is proposed. Specifically, each individual is assigned two rankings: one ranking calculated based on Pareto dominance (regardless of constraints) and another calculated based on the constrained dominance principle (CDP). The fitness value of an individual is the weighted sum of these two rankings, and the weight is related to the generation number and the proportion of feasible solutions in the current generation. Based on the proposed CHT, a constrained multiobjective differential evolution algorithm is proposed. To generate high-quality offspring, the proposed constrained multiobjective differential evolution algorithm combines four mutation operations as core components of the search algorithm. The proposed algorithm is compared with eight state-of-the-art algorithms in experiments with five test suites, and the experimental results show that the proposed algorithm performs significantly better than the eight state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we propose a multi-cycled sequential memetic computing structure for constrained optimisation. The structure is composed of multiple evolutionary cycles. At each cycle, an evolutionary algorithm is considered as an operator, and connects with a local optimiser. This structure enables the learning of useful knowledge from previous cycles and the transfer of the knowledge to facilitate search in latter cycles. Specifically, we propose to apply an estimation of distribution algorithm (EDA) to explore the search space until convergence at each cycle. A local optimiser, called DONLP2, is then applied to improve the best solution found by the EDA. New cycle starts after the local improvement if the computation budget has not been exceeded. In the developed EDA, an adaptive fully-factorized multivariate probability model is proposed. A learning mechanism, implemented as the guided mutation operator, is adopted to learn useful knowledge from previous cycles. The developed algorithm was experimentally studied on the benchmark problems in the CEC 2006 and 2010 competition. Experimental studies have shown that the developed probability model exhibits excellent exploration capability and the learning mechanism can significantly improve the search efficiency under certain conditions. The comparison against some well-known algorithms showed the superiority of the developed algorithm in terms of the consumed fitness evaluations and the solution quality. [ABSTRACT FROM AUTHOR]