The performance of a deep neural network is heavily dependent on its architecture and various neural architecture search strategies have been developed for automated network architecture design. Recently, evolutionary neural architecture search (ENAS) has received increasing attention due to the attractive global optimization capability of evolutionary algorithms. However, ENAS suffers from extremely high computation costs because a large number of performance evaluations is usually required in evolutionary optimization and training deep neural networks is itself computationally very intensive. To address this issue, this paper proposes a new evolutionary framework for fast ENAS based on directed acyclic graph, in which parents are randomly sampled and trained on each mini-batch of training data. In addition, a node inheritance strategy is adopted to generate offspring individuals and their fitness is directly evaluated without training. To enhance the feature processing capability of the evolved neural networks, we also encode a channel attention mechanism in the search space. We evaluate the proposed algorithm on the widely used datasets, in comparison with 26 state-of-the-art peer algorithms. Our experimental results show the proposed algorithm is not only computationally much more efficiently, but also highly competitive in learning performance.
Diversity is an important factor in evolutionary algorithms to prevent premature convergence towards a single local optimum. In order to maintain diversity throughout the process of evolution, various means exist in literature. We analyze approaches to diversity that (a) have an explicit and quantifiable influence on fitness at the individual level and (b) require no (or very little) additional domain knowledge such as domain-specific distance functions. We also introduce the concept of genealogical diversity in a broader study. We show that employing these approaches can help evolutionary alg…
Weight initialization is critical in being able to successfully train artificial neural networks (ANNs), and even more so for recurrent neural networks (RNNs) which can easily suffer from vanishing and exploding gradients. In neuroevolution, where evolutionary algorithms are applied to neural architecture search, weights typically need to be initialized at three different times: when initial genomes (ANN architectures) are created at the beginning of the search, when offspring genomes are generated by crossover, and when new nodes or edges are created during mutation. This work explores the di…
University of Southampton（南安普顿大学）；The Alan Turing Institute（阿兰·图灵研究所）
Evolutionary Computation is a group of biologically inspired algorithms used to solve complex optimisation problems. It can be split into Evolutionary Algorithms, which take inspiration from genetic inheritance, and Swarm Intelligence algorithms, that take inspiration from cultural inheritance. However, recent developments have focused on computational or mathematical adaptions, leaving their biological roots behind. This has left much of the modern evolutionary literature relatively unexplored. To understand which evolutionary mechanisms have been considered, and which have been overlooked, t…
University of Southampton（南安普顿大学）；National Oceanography Centre（国家海洋学中心）；The Alan Turing Institute（艾伦·图灵研究所）
Hundreds of Evolutionary Computation approaches have been reported. From an evolutionary perspective they focus on two fundamental mechanisms: cultural inheritance in Swarm Intelligence and genetic inheritance in Evolutionary Algorithms. Contemporary evolutionary biology looks beyond genetic inheritance, proposing a so-called ``Extended Evolutionary Synthesis''. Many concepts from the Extended Evolutionary Synthesis have been left out of Evolutionary Computation as interest has moved toward specific implementations of the same general mechanisms. One such concept is epigenetic inheritance, whi…
Based on the framework of the quantum-inspired evolutionary algorithm, a cuckoo quantum evolutionary algorithm (CQEA) is proposed for solving the graph coloring problem (GCP). To reduce iterations for the search of the chromatic number, the initial quantum population is generated by random initialization assisted by inheritance. Moreover, improvement of global exploration is achieved by incorporating the cuckoo search strategy, and a local search operation, as well as a perturbance strategy, is developed to enhance its performance on GCPs. Numerical results demonstrate that CQEA operates with …
Many real-world control and classification tasks involve a large number of features. When artificial neural networks (ANNs) are used for modeling these tasks, the network architectures tend to be large. Neuroevolution is an effective approach for optimizing ANNs; however, there are two bottlenecks that make their application challenging in case of high-dimensional networks using direct encoding. First, classic evolutionary algorithms tend not to scale well for searching large parameter spaces; second, the network evaluation over a large number of training instances is in general time-consuming…
Convolutional neural networks belong to the most successul image classifiers, but the adaptation of their network architecture to a particular problem is computationally expensive. We show that an evolutionary algorithm saves training time during the network architecture optimization, if learned network weights are inherited over generations by Lamarckian evolution. Experiments on typical image datasets show similar or significantly better test accuracies and improved convergence speeds compared to two different baselines without weight inheritance. On CIFAR-10 and CIFAR-100 a 75 % improvement…
Due to the nonlinearity of artificial neural networks, designing topologies for deep convolutional neural networks (CNN) is a challenging task and often only heuristic approach, such as trial and error, can be applied. An evolutionary algorithm can solve optimization problems where the fitness landscape is unknown. However, evolutionary algorithms are computing resource intensive, which makes it difficult for problems when deep CNNs are involved. In this paper, we propose an evolutionary strategy to find better topologies for deep CNNs. Incorporating the concept of knowledge inheritance and kn…
Edinburgh Napier University（爱丁堡龙比亚大学）；University of York（约克大学）；University of the West of England（西英格兰大学）；University of Sunderland（桑德兰大学）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
The joint optimisation of body-plan and control via evolutionary processes can be challenging in rich morphological spaces in which offspring can have body-plans that are very different from either of their parents. This causes a potential mismatch between the structure of an inherited controller and the new body. To address this, we propose a framework that combines an evolutionary algorithm to generate body-plans and a learning algorithm to optimise the parameters of a neural controller. The topology of this controller is created once the body-plan of each offspring body-plan is generated. T…
A novel multi-agent evolutionary robotics (ER) based framework, inspired by competitive evolutionary environments in nature, is demonstrated for training Spiking Neural Networks (SNN). The weights of a population of SNNs along with morphological parameters of bots they control in the ER environment are treated as phenotypes. Rules of the framework select certain bots and their SNNs for reproduction and others for elimination based on their efficacy in capturing food in a competitive environment. While the bots and their SNNs are given no explicit reward to survive or reproduce via any loss fun…
A method to control results of gradient descent unsupervised learning in a deep neural network by using evolutionary algorithm is proposed. To process crossover of unsupervisedly trained models, the algorithm evaluates pointwise fitness of individual nodes in neural network. Labeled training data is randomly sampled and breeding process selects nodes by calculating degree of their consistency on different sets of sampled data. This method supervises unsupervised training by evolutionary process. We also introduce modified Restricted Boltzmann Machine which contains repulsive force among nodes …
Many biological processes have been the source of inspiration for heuristic methods that generate high-quality solutions to solve optimization and search problems. This thesis presents an epigenetic technique for Evolutionary Algorithms, inspired by the epigenetic regulation process, a mechanism to better understand the ability of individuals to adapt and learn from the environment. Epigenetic regulation comprises biological mechanisms by which small molecules, also known as epigenetic tags, are attached to or removed from a particular gene, affecting the phenotype. Five fundamental elements f…
Inverted Generational Distance (IGD) has been widely considered as a reliable performance indicator to concurrently quantify the convergence and diversity of multi- and many-objective evolutionary algorithms. In this paper, an IGD indicator-based evolutionary algorithm for solving many-objective optimization problems (MaOPs) has been proposed. Specifically, the IGD indicator is employed in each generation to select the solutions with favorable convergence and diversity. In addition, a computationally efficient dominance comparison method is designed to assign the rank values of solutions along…
Hamilton College（汉密尔顿学院）；Amherst College（阿默斯特学院）；Hampshire College（汉普郡学院）；University of Massachusetts（马萨诸塞大学）
In genetic programming, an evolutionary method for producing computer programs that solve specified computational problems, parent selection is ordinarily based on aggregate measures of performance across an entire training set. Lexicase selection, by contrast, selects on the basis of performance on random sequences of training cases; this has been shown to enhance problem-solving power in many circumstances. Lexicase selection can also be seen as better reflecting biological evolution, by modeling sequences of challenges that organisms face over their lifetimes. Recent work has demonstrated t…
Southern University of Science and Technology（南方科技大学）；City University of Hong Kong（香港城市大学）；University of Surrey（萨里大学）
Recently, increasing works have proposed to drive evolutionary algorithms using machine learning models. Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models. Since it usually requires a certain amount of data (i.e. the candidate solutions generated by the algorithms) for model training, the performance deteriorates rapidly with the increase of the problem scales, due to the curse of dimensionality. To address this issue, we propose a multi-objective evolutionary algorithm driven by the generative adversarial n…
Vanilla neural architecture search using evolutionary algorithms (EA) involves evaluating each architecture by training it from scratch, which is extremely time-consuming. This can be reduced by using a supernet to estimate the fitness of every architecture in the search space due to its weight sharing nature. However, the estimated fitness is very noisy due to the co-adaptation of the operations in the supernet. In this work, we propose a method called pEvoNAS wherein the whole neural architecture search space is progressively reduced to smaller search space regions with good architectures. T…
Recently, more and more works have proposed to drive evolutionary algorithms using machine learning models.Usually, the performance of such model based evolutionary algorithms is highly dependent on the training qualities of the adopted models.Since it usually requires a certain amount of data (i.e. the candidate solutions generated by the algorithms) for model training, the performance deteriorates rapidly with the increase of the problem scales, due to the curse of dimensionality.To address this issue, we propose a multi-objective evolutionary algorithm driven by the generative adversarial n…
Neuro-Evolutionary Approach to Physics-Aware Symbolic Regression
Czech Institute of Informatics, Robotics, and Cybernetics CTU in Prague（捷克信息学、机器人学和自动化研究中心CTU布拉格分校）；Dept. of Cognitive Robotics, TU Delft（认知机器人学系代尔夫特理工大学）；CIIRC, CTU in Prague（智能信息研究中心CTU布拉格分校）
Black-box complexity theory provides lower bounds for the runtime of black-box optimizers like evolutionary algorithms and serves as an inspiration for the design of new genetic algorithms. Several black-box models covering different classes of algorithms exist, each highlighting a different aspect of the algorithms under considerations. In this work we add to the existing black-box notions a new \emph{elitist black-box model}, in which algorithms are required to base all decisions solely on (a fixed number of) the best search points sampled so far. Our model combines features of the ranking-b…
Variable Search Stepsize for Randomized Local Search in Multi-Objective Combinatorial Optimization
School of Computer, China University of Geosciences（中国地质大学计算机学院）；Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software, Ministry of Education（教育部自然资源信息管理与数字孪生工程软件工程研究中心）；Hubei Key Laboratory of Intelligent Geo-Information Processing（湖北省智能地理信息处理重点实验室）；School of Computer, Science and Informatics, De Montfort University（德蒙福特大学计算机、科学与信息学院）；School of Computer Science, University of Birmingham（伯明翰大学计算机科学学院）；School of Chemical Engineering, University of Birmingham（伯明翰大学化学工程学院）
Estimation-of-distribution algorithms (EDAs) are randomized search heuristics that create a probabilistic model of the solution space, which is updated iteratively, based on the quality of the solutions sampled according to the model. As previous works show, this iteration-based perspective can lead to erratic updates of the model, in particular, to bit-frequencies approaching a random boundary value. In order to overcome this problem, we propose a new EDA based on the classic compact genetic algorithm (cGA) that takes into account a longer history of samples and updates its model only with re…
Neural Architecture Search (NAS) is emerging as a new research direction which has the potential to replace the hand-crafted neural architectures designed for specific tasks. Previous evolution based architecture search requires high computational resources resulting in high search time. In this work, we propose a novel way of applying a simple genetic algorithm to the NAS problem called EvNAS (Evolving Neural Architecture using One Shot Model) which reduces the search time significantly while still achieving better result than previous evolution based methods. The architectures are represente…
Evolutionary Optimization of Physics-Informed Neural Networks: Advancing Generalizability by the Baldwin Effect
Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore（高性能计算研究所，科技研究局，新加坡）；School of Mechanical Sciences, Indian Institute of Technology Goa, India（机械科学学院，印度理工学院 Goa）；College of Computing and Data Science, Nanyang Technological University, Singapore（计算与数据科学学院，南洋理工大学）；Technology Centre for Offshore and Marine, Singapore（海上与海洋技术中心，新加坡）；Agency for Science, Technology and Research, Singapore（科技研究局，新加坡）
Understanding how the time-complexity of evolutionary algorithms (EAs) depend on their parameter settings and characteristics of fitness landscapes is a fundamental problem in evolutionary computation. Most rigorous results were derived using a handful of key analytic techniques, including drift analysis. However, since few of these techniques apply effortlessly to population-based EAs, most time-complexity results concern simplified EAs, such as the (1+1) EA. This paper describes the level-based theorem, a new technique tailored to population-based processes. It applies to any non-elitist pro…
Optimization Geometry of QAOA and Variational Quantum Algorithms
VSB – Technical University of Ostrava（俄斯特拉发科技大学）；IT4Innovations National Supercomputing Center, VSB – Technical University of Ostrava（俄斯特拉发科技大学 IT4创新国家超算中心）；Klaipeda University（克莱佩达大学）；Gran Sasso Science Institute（格兰萨索科学研究所）；Indian Statistical Institute（印度统计研究所）；Università dell’Aquila（阿奎拉大学）
NOVA LINCS（NOVA LINCS 实验室）；Universidade da Beira Interior（贝拉内政大学）
Neural Architecture Search has achieved state-of-the-art performance in a variety of tasks, out-performing human-designed networks. However, many assumptions, that require human definition, related with the problems being solved or the models generated are still needed: final model architectures, number of layers to be sampled, forced operations, small search spaces, which ultimately contributes to having models with higher performances at the cost of inducing bias into the system. In this paper, we propose HMCNAS, which is composed of two novel components: i) a method that leverages informati…
