Evolutionary Computation has been successfully used to synthesise controllers for embodied agents and multi-agent systems in general. Notwithstanding this, continuous on-line adaptation by the means of evolutionary algorithms is still under-explored, especially outside the evolutionary robotics domain. In this paper, we present an on-line evolutionary programming algorithm that searches in the agent design space for the appropriate behavioural policies to cope with the underlying environment. We discuss the current problems of continuous agent adaptation, present our on-line evolution testbed for evolutionary simulation.
In this paper we analyze the cryptanalysis of the simplified data encryption standard algorithm using meta-heuristics and in particular genetic algorithms. The classic fitness function when using such an algorithm is to compare n-gram statistics of a the decrypted message with those of the target message. We show that using such a function is irrelevant in case of Genetic Algorithm, simply because there is no correlation between the distance to the real key (the optimum) and the value of the fitness, in other words, there is no hidden gradient. In order to emphasize this assumption we experimentally show that a genetic algorithm perform worse than a random search on the cryptanalysis of the simplified data encryption standard algorithm.
In today's global business market place, individual firms no longer compete as independent entities with unique brand names but as integral part of supply chain links. Key to success of any business is satisfying customer's demands on time which may result in cost reductions and increase in service level. In supply chain networks decisions are made with uncertainty about product's demands, costs, prices, lead times, quality in a competitive and collaborative environment. If poor decisions are made, they may lead to excess inventories that are costly or to insufficient inventory that cannot meet customer's demands. In this work we developed a bi-objective model that minimizes system wide costs of the supply chain and delays on delivery of products to distribution centers for a three echelon supply chain. Picking a set of Pareto front for multi-objective optimization problems require robust and efficient methods that can search an entire space. We used evolutionary algorithms to find the set of Pareto fronts which have proved to be effective in finding the entire set of Pareto fronts.
Differential Evolution (DE) is a renowned optimization stratagem that can easily solve nonlinear and comprehensive problems. DE is a well known and uncomplicated population based probabilistic approach for comprehensive optimization. It has apparently outperformed a number of Evolutionary Algorithms and further search heuristics in the vein of Particle Swarm Optimization at what time of testing over both yardstick and actual world problems. Nevertheless, DE, like other probabilistic optimization algorithms, from time to time exhibits precipitate convergence and stagnates at suboptimal position. In order to stay away from stagnation behavior while maintaining an excellent convergence speed, an innovative search strategy is introduced, named memetic search in DE. In the planned strategy, positions update equation customized as per a memetic search stratagem. In this strategy a better solution participates more times in the position modernize procedure. The position update equation is inspired from the memetic search in artificial bee colony algorithm. The proposed strategy is named as Memetic Search in Differential Evolution (MSDE). To prove efficiency and efficacy of MSDE, it is tested over 8 benchmark optimization problems and three real world optimization problems. A comparative analysis has also been carried out among proposed MSDE and original DE. Results show that the anticipated algorithm go one better than the basic DE and its recent deviations in a good number of the experiments.
The balance of exploration versus exploitation (EvE) is a key issue on evolutionary computation. In this paper we will investigate how an adaptive controller aimed to perform Operator Selection can be used to dynamically manage the EvE balance required by the search, showing that the search strategies determined by this control paradigm lead to an improvement of solution quality found by the evolutionary algorithm.
Some experimental investigations have shown that evolutionary algorithms (EAs) are efficient for the minimum label spanning tree (MLST) problem. However, we know little about that in theory. As one step towards this issue, we theoretically analyze the performances of the (1+1) EA, a simple version of EAs, and a multi-objective evolutionary algorithm called GSEMO on the MLST problem. We reveal that for the MLST$_{b}$ problem the (1+1) EA and GSEMO achieve a $\frac{b+1}{2}$-approximation ratio in expected polynomial times of $n$ the number of nodes and $k$ the number of labels. We also show that GSEMO achieves a $(2ln(n))$-approximation ratio for the MLST problem in expected polynomial time of $n$ and $k$. At the same time, we show that the (1+1) EA and GSEMO outperform local search algorithms on three instances of the MLST problem. We also construct an instance on which GSEMO outperforms the (1+1) EA.
This work studies the behavior of three elitist multi- and many-objective evolutionary algorithms generating a high-resolution approximation of the Pareto optimal set. Several search-assessment indicators are defined to trace the dynamics of survival selection and measure the ability to simultaneously keep optimal solutions and discover new ones under different population sizes, set as a fraction of the size of the Pareto optimal set.
Evolutionary algorithms (EA) have been widely accepted as efficient solvers for complex real world optimization problems, including engineering optimization. However, real world optimization problems often involve uncertain environment including noisy and/or dynamic environments, which pose major challenges to EA-based optimization. The presence of noise interferes with the evaluation and the selection process of EA, and thus adversely affects its performance. In addition, as presence of noise poses challenges to the evaluation of the fitness function, it may need to be estimated instead of being evaluated. Several existing approaches attempt to address this problem, such as introduction of diversity (hyper mutation, random immigrants, special operators) or incorporation of memory of the past (diploidy, case based memory). However, these approaches fail to adequately address the problem. In this paper we propose a Distributed Population Switching Evolutionary Algorithm (DPSEA) method that addresses optimization of functions with noisy fitness using a distributed population switching architecture, to simulate a distributed self-adaptive memory of the solution space. Local regression is used in the pseudo-populations to estimate the fitness. Successful applications to benchmark test problems ascertain the proposed method's superior performance in terms of both robustness and accuracy.
We re-investigate a fundamental question: how effective is crossover in Genetic Algorithms in combining building blocks of good solutions? Although this has been discussed controversially for decades, we are still lacking a rigorous and intuitive answer. We provide such answers for royal road functions and OneMax, where every bit is a building block. For the latter we show that using crossover makes every ($\mu$+$\lambda$) Genetic Algorithm at least twice as fast as the fastest evolutionary algorithm using only standard bit mutation, up to small-order terms and for moderate $\mu$ and $\lambda$. Crossover is beneficial because it effectively turns fitness-neutral mutations into improvements by combining the right building blocks at a later stage. Compared to mutation-based evolutionary algorithms, this makes multi-bit mutations more useful. Introducing crossover changes the optimal mutation rate on OneMax from $1/n$ to $(1+\sqrt{5})/2 \cdot 1/n \approx 1.618/n$. This holds both for uniform crossover and $k$-point crossover. Experiments and statistical tests confirm that our findings apply to a broad class of building-block functions.
In many publications, authors showed that chaotic pseudo random number generators (PRNGs) may improve performance of the evolutionary algorithms. In this paper, we use two chaotic maps Gingerbread man and Tinkerbell as the chaotic PRNGs instead of the classical PRNG in the differential evolution. Numbers generated by this maps are normalized to the unit interval by three different methods -- operation modulo, straightforward number normalization where we know minimal and maximal generated number and arctangent of the two variables $x$ and $y$, where numbers $x$ and $y$ are generated by the Gingerbread man map and Tinkerbell map. The first goal of this paper is to show whether the differential evolution convergence speed might be affected by the way how we normalize number generated by the chaotic map. The second goal is to find out the influence of the probability distribution function of the selected chaotic PRNGs. The results mentioned below showed that the selected normalization method may improve differential evolution convergence speed, especially in the case of arctangent and straightforward number normalization, where we know the minimal and maximal generated numbers.
Most experimental studies initialize the population of evolutionary algorithms with random genotypes. In practice, however, optimizers are typically seeded with good candidate solutions either previously known or created according to some problem-specific method. This "seeding" has been studied extensively for single-objective problems. For multi-objective problems, however, very little literature is available on the approaches to seeding and their individual benefits and disadvantages. In this article, we are trying to narrow this gap via a comprehensive computational study on common real-valued test functions. We investigate the effect of two seeding techniques for five algorithms on 48 optimization problems with 2, 3, 4, 6, and 8 objectives. We observe that some functions (e.g., DTLZ4 and the LZ family) benefit significantly from seeding, while others (e.g., WFG) profit less. The advantage of seeding also depends on the examined algorithm.
Finding a good classifier is a multiobjective optimization problem with different error rates and the costs to be minimized. The receiver operating characteristic is widely used in the machine learning community to analyze the performance of parametric classifiers or sets of Pareto optimal classifiers. In order to directly compare two sets of classifiers the area (or volume) under the convex hull can be used as a scalar indicator for the performance of a set of classifiers in receiver operating characteristic space. Recently, the convex hull based multiobjective genetic programming algorithm was proposed and successfully applied to maximize the convex hull area for binary classification problems. The contribution of this paper is to extend this algorithm for dealing with higher dimensional problem formulations. In particular, we discuss problems where parsimony (or classifier complexity) is stated as a third objective and multi-class classification with three different true classification rates to be maximized. The design of the algorithm proposed in this paper is inspired by indicator-based evolutionary algorithms, where first a performance indicator for a solution set is established and then a selection operator is designed that complies with the performance indicator. In this case, the performance indicator will be the volume under the convex hull. The algorithm is tested and analyzed in a proof of concept study on different benchmarks that are designed for measuring its capability to capture relevant parts of a convex hull. Further benchmark and application studies on email classification and feature selection round up the analysis and assess robustness and usefulness of the new algorithm in real world settings.
Many problems are related to network projects, such as electric distribution, telecommunication and others. Most of them can be represented by graphs, which manipulate thousands or millions of nodes, becoming almost an impossible task to obtain real-time solutions. Many efficient solutions use Evolutionary Algorithms (EA), where researches show that performance of EAs can be substantially raised by using an appropriate representation, such as the Node-Depth Encoding (NDE). The objective of this work was to partition an implementation on single-FPGA (Field-Programmable Gate Array) based on NDE from 512 nodes to a multi-FPGAs approach, expanding the system to 4096 nodes.
We present a technique for developing a network of re-used features, where the topology is formed using a coarse learning method, that allows gradient-descent fine tuning, known as an Abstract Deep Network (ADN). New features are built based on observed co-occurrences, and the network is maintained using a selection process related to evolutionary algorithms. This allows coarse ex- ploration of the problem space, effective for irregular domains, while gradient descent allows pre- cise solutions. Accuracy on standard UCI and Protein-Structure Prediction problems is comparable with benchmark SVM and optimized GBML approaches, and shows scalability for addressing large problems. The discrete implementation is symbolic, allowing interpretability, while the continuous method using fine-tuning shows improved accuracy. The binary multiplexer problem is explored, as an irregular domain that does not support gradient descent learning, showing solution to the bench- mark 135-bit problem. A convolutional implementation is demonstrated on image classification, showing an error-rate of 0.79% on the MNIST problem, without a pre-defined topology. The ADN system provides a method for developing a very sparse, deep feature topology, based on observed relationships between features, that is able to find solutions in irregular domains, and initialize a network prior to gradient descent learning.
In this paper, we study the impact of selection methods in the context of on-line on-board distributed evolutionary algorithms. We propose a variant of the mEDEA algorithm in which we add a selection operator, and we apply it in a taskdriven scenario. We evaluate four selection methods that induce different intensity of selection pressure in a multi-robot navigation with obstacle avoidance task and a collective foraging task. Experiments show that a small intensity of selection pressure is sufficient to rapidly obtain good performances on the tasks at hand. We introduce different measures to compare the selection methods, and show that the higher the selection pressure, the better the performances obtained, especially for the more challenging food foraging task.
An initial study of surrogate-assisted evolutionary algorithms used to design vertical-axis wind turbines wherein candidate prototypes are evaluated under fan generated wind conditions after being physically instantiated by a 3D printer has recently been presented. Unlike other approaches, such as computational fluid dynamics simulations, no mathematical formulations were used and no model assumptions were made. This paper extends that work by exploring alternative surrogate modelling and evolutionary techniques. The accuracy of various modelling algorithms used to estimate the fitness of evaluated individuals from the initial experiments is compared. The effect of temporally windowing surrogate model training samples is explored. A surrogate-assisted approach based on an enhanced local search is introduced; and alternative coevolution collaboration schemes are examined.
Optimization techniques are frequently applied in science and engineering research and development. Evolutionary algorithms, as a kind of general-purpose metaheuristic, have been shown to be very effective in solving a wide range of optimization problems. A recently proposed chemical-reaction-inspired metaheuristic, Chemical Reaction Optimization (CRO), has been applied to solve many global optimization problems. However, the functionality of the inter-molecular ineffective collision operator in the canonical CRO design overlaps that of the on-wall ineffective collision operator, which can potential impair the overall performance. In this paper we propose a new inter-molecular ineffective collision operator for CRO for global optimization. To fully utilize our newly proposed operator, we also design a scheme to adapt the algorithm to optimization problems with different search space characteristics. We analyze the performance of our proposed algorithm with a number of widely used benchmark functions. The simulation results indicate that the new algorithm has superior performance over the canonical CRO.
Evolutionary algorithms (EAs) are very popular tools to design and evolve artificial neural networks (ANNs), especially to train them. These methods have advantages over the conventional backpropagation (BP) method because of their low computational requirement when searching in a large solution space. In this paper, we employ Chemical Reaction Optimization (CRO), a newly developed global optimization method, to replace BP in training neural networks. CRO is a population-based metaheuristics mimicking the transition of molecules and their interactions in a chemical reaction. Simulation results show that CRO outperforms many EA strategies commonly used to train neural networks.
The hardness of fitness functions is an important research topic in the field of evolutionary computation. In theory, the study can help understanding the ability of evolutionary algorithms. In practice, the study may provide a guideline to the design of benchmarks. The aim of this paper is to answer the following research questions: Given a fitness function class, which functions are the easiest with respect to an evolutionary algorithm? Which are the hardest? How are these functions constructed? The paper provides theoretical answers to these questions. The easiest and hardest fitness functions are constructed for an elitist (1+1) evolutionary algorithm to maximise a class of fitness functions with the same optima. It is demonstrated that the unimodal functions are the easiest and deceptive functions are the hardest in terms of the time-fitness landscape. The paper also reveals that the easiest fitness function to one algorithm may become the hardest to another algorithm, and vice versa.
From the era of big science we are back to the "do it yourself", where you do not have any money to buy clusters or subscribe to grids but still have algorithms that crave many computing nodes and need them to measure scalability. Fortunately, this coincides with the era of big data, cloud computing, and browsers that include JavaScript virtual machines. Those are the reasons why this paper will focus on two different aspects of volunteer or freeriding computing: first, the pragmatic: where to find those resources, which ones can be used, what kind of support you have to give them; and then, the theoretical: how evolutionary algorithms can be adapted to an environment in which nodes come and go, have different computing capabilities and operate in complete asynchrony of each other. We will examine the setup needed to create a very simple distributed evolutionary algorithm using JavaScript and then find a model of how users react to it by collecting data from several experiments featuring different classical benchmark functions.