Search

The last 2 decades have seen the emergence of a large number of computational intelligence techniques derived from thenatural sciences.Newnature-inspiredproblem-solving paradigms emerged that are based on Darwinian evolution, entomology, condensed matter physics, neurobiology, immunology, etc. These paradigms, in turn, popularized search methodologies such as Genetic Algorithms, Genetic Programming, Evolution Strategies, Particle Swarm Optimization, Ant Colony Optimization, Simulated Annealing, Neural Networks, Artificial Immune Systems, etc. At the same time, other search methodologies such as Tabu-search, Scatter Search, GRASP, etc, remained “metaphor-less”. A war-of-the-method ensued and continues, often it is the case that each of these search paradigmshas a nicheflagship publication where the latest advances within the paradigm are presented. The IEEE Transactions on Evolutionary Algorithms or its twin publication on Neural Networks, the Evolutionary Computation journal, the journal of Genetic Programming and Evolvable Machines, the Swarm Intelligence Journal, etc, are examples of scientific outlets for work derived from nature-inspired principles, while the Journal of Heuristics, the Journal of Soft Computing—A Fusion of Foundations, Methodologies and Applications or the more recent International Journal ofMetaheuristics are examples of publications where the research emphasis is not necessarily on natural computation.

We describe the development and application of an imaging protocol, which evolves a scanning probe’s atomic structure in parallel with automated optimization of the scan parameters. Our protocol coerces the system into a state that produces a specific atomic resolution image type without human involvement.

Novel boronate-based chemical ensembles have been constructed that exhibit reversible responses comparable to re-settable logic functions according to the rational coupling of the molecular components.

Unconventional computing is an area of research in which novel materials and paradigms are utilised to implement computation. Previously we have demonstrated how registers, logic gates and logic circuits can be implemented, unconventionally, with a biocompatible molecular switch, NitroBIPS, embedded in a polymer matrix. NitroBIPS and related molecules have been shown elsewhere to be capable of modifying many biological processes in a manner that is dependent on its molecular form. Thus, one possible application of this type of unconventional computing is to embed computational processes into biological systems. Here we expand on our earlier proof-of-principle work and demonstrate that universal computation can be implemented using NitroBIPS. We have previously shown that spatially localised computational elements, including registers and logic gates, can be produced. We explain how parallel registers can be implemented, then demonstrate an application of parallel registers in the form of Turing machine tapes, and demonstrate both parallel registers and logic circuits in the form of elementary cellular automata. The Turing machines and elementary cellular automata utilise the same samples and same hardware to implement their registers, logic gates and logic circuits; and both represent examples of universal computing paradigms. This shows that homogenous photochromic computational devices can be dynamically repurposed without invasive reconfiguration. The result represents an important, necessary step towards demonstrating the general feasibility of interfacial computation embedded in biological systems or other unconventional materials and environments.

Self-assembly is a powerful autopoietic mechanism ubiquitous throughout the natural world. It may be found at the molecular scale and also at astronomical scales. Self-assembly power lays in the fact that it is a distributed, not necessarily synchronous, control mechanism for the bottom-up manufacture of complex systems. Control of the assembly process is shared across a myriad of elemental components, none of which has either the storage or the computation capabilities to know and follow a master plan for the assembly of the intended system. In this paper we present an evolutionary algorithm which is capable of programming the so called "Wang tiles" for the self-assembly of two-dimensional squares.

The prediction of the coordination number (CN) of an amino acid in a protein structure has recently received renewed attention. In a recent paper, Kinjo et al. proposed a real-valued definition of CN and a criterion to map it onto a finite set of classes, in order to predict it using classification approaches. The literature reports several kinds of input information used for CN prediction. The aim of this paper is to assess the performance of a state-of-the-art learning method, Learning Classifier Systems (LCS) on this CN definition, with various degrees of precision, based on several combinations of input attributes. Moreover, we will compare the LCS performance to other well-known learning techniques. Our experiments are also intended to determinethe minimum set of input information needed to achieve good predictive performance, so as to generate competent yet simple and interpretable classification rules. Thus, the generated predictors (rule sets) are analyzed for their interpretability.

This paper reports an improvement to genetic programming (GP) search for the symbolic regression domain, based on an analysis of dissimilarity and mating. GP search is generally difficult to characterise for this domain, preventing well motivated algorithmic improvements. We first examine the ability of various solutions to contribute to the search process. Further analysis highlights the numerous solutions produced during search with no change to solution quality. A simple algorithmic enhancement is made that reduces these events and produces a statistically significant improvement in solution quality. We conclude by verifying the generalisability of these results on several other regression instances

The acquisition of biological data, ranging from molecular characterization and simulations (e.g. protein fold- ing dynamics), to systems biology endeavors (e.g. whole organ simulations) all the way up to ecological observations (e.g. as to ascertain climate change's impact on the biota) is growing at unprecedented speed. The use of computational and networking resources is thus unavoidable. As the datasets become bigger and the acquisition technology more refined, the biologist is empowered to ask deeper and more complex questions. These, in turn, drive a runoff effect where large re- search consortia emerge that span beyond organizations and national boundaries. Thus the need for reliable, robust, certi- fied, curated, accessible, secure and timely data processing and management becomes entrenched within, and crucial to, 21 st century biology. Furthermore, the proliferation of biotechnologies and advances in biological sciences has produced a strong drive for new informatics solutions, both at the basic science and technological levels. The previously unknown situation of dealing with, on one hand, (potentially) exabytes of data, much of which is noisy, has large experimental er- rors or theoretical uncertainties associated with it, or on the other hand, large quantities of data that require automated computationally intense analysis and processing, have produced important innovations in web and grid technology. In this paper we present a trace of these technological changes in Web and Grid technology, including details of emerging infra- structures, standards, languages and tools, as they apply to bioinformatics, computational biology and systems biology. A major focus of this technological review is to collate up-to-date information regarding the design and implementation of various bioinformatics Webs, Grids, Web-based grids or Grid-based webs in terms of their infrastructure, standards, pro- tocols, services, applications and other tools. This review, besides surveying the current state-of-the-art, will also provide a road map for future research and open questions.

We introduce a model of self-assembly P systems as devices that use some of the features of population P systems to progressively grow a graph structure by forming new bonds between the existing cells and some new cells which are brought into the system step by step. The new cells are then able to self-assemble locally either at the level of cells or at the level of neighbourhoods of cells by using bond-making rules according to a specific self-assembly model. We describe two self-assembly models, called respectively parallel single-point self-assembly and parallel multi-point self-assembly. Then, we precisely state the problem of programmable self-assembly for P systems as the problem of uniquely generating a given graph by means of self-assembly P systems. In this respect, we show how to define a self-assembly P systems that uniquely generates a complete binary tree by using a “minimal” set of resources.

This paper proposes a new smart crossover operator for a Pittsburgh Learning Classifier System. This operator, unlike other recent LCS approaches of smart recombination, does not learn the structure of the domain, but it merges the rules of N parents (N ≥ 2) to generate a new offspring. This merge process uses an heuristic that selects the minimum subset of candidate rules that obtains maximum training accuracy. Moreover the operator also includes a rule pruning scheme to avoid the inclusion of over-specific rules, and to guarantee as much as possible the robust behaviour of the LCS. This operator takes advantage from the fact that each individual in a Pittsburgh LCS is a complete solution, and the system has a global view of the solution space that the proposed rule selection algorithm exploits. We have empirically evaluated this operator using a recent LCS called GAssist. First with the standard LCS benchmark, the 11 bits multiplexer, and later using 25 standard real datasets. The results of the experiments over these datasets indicate that the new operator manages to increase the accuracy of the system over the classical crossover in 16 of the 25 datasets, and never having a significantly worse performance than the classic operator.

In this paper we propose an immune algorithm ( IA ) to solve high dimensional global optimization problems. To evaluate the effectiveness and quality of the IA we performed a large set of unconstrained numerical optimisation experiments, which is a crucial component of many real-world problem-solving settings. We extensively compare the IA against several Differential Evolution (DE) algorithms as these have been shown to perform better than many other Evolutionary Algorithms on similar problems. The DE algorithms were implemented using a range of recombination and mutation operators combinations. The algorithms were tested on 13 well known benchmark problems. Our results show that the proposed IA is effective, in terms of accuracy, and capable of solving large-scale instances of our benchmarks. We also show that the IA is comparable, and often outperforms, all the DE variants, including two Memetic algorithms.

This paper presents a set of experiments on the use of Learning Classifier Systems for the purpose of solving combinatorial optimisation problems. We demonstrate our approach with a set of Fractal Travelling Salesman Problem (TSP) instances for which it is possible to know by construction the optimal tour regardless of the number of cities in them. This special type of TSP instances are ideal for testing new methods as they are well characterised in their solvability and easy to use for scalability studies. Our results show that an LCS is capable of learning rules to recognise to which family of instances a set containing a sample of the cities in the problem belongs to and hence automatically select the best heuristic to solve it. Moreover, we have also trained the LCS to recognise links belonging to the optimal tour.

This paper introduces the Tree-String problem for genetic programming and related search and optimisation methods. To improve the understanding of optimisation and search methods, we aim to capture the complex dynamic created by the interdependencies of solution structure and content. Thus, we created an artificial domain that is amenable for analysis, yet representative of a wide-range of real-world applications. The Tree-String problem provides several benefits, including: the direct control of both structure and content objectives, the production of a rich and representative search space, the ability to create tunably difficult and random instances and the flexibility for specialisation.

Background We investigate automated and generic alphabet reduction techniques for protein structure prediction datasets. Reducing alphabet cardinality without losing key biochemical information opens the door to potentially faster machine learning, data mining and optimization applications in structural bioinformatics. Furthermore, reduced but informative alphabets often result in, e.g., more compact and human-friendly classification/clustering rules. In this paper we propose a robust and sophisticated alphabet reduction protocol based on mutual information and state-of-the-art optimization techniques. Results We applied this protocol to the prediction of two protein structural features: contact number and relative solvent accessibility. For both features we generated alphabets of two, three, four and five letters. The five-letter alphabets gave prediction accuracies statistically similar to that obtained using the full amino acid alphabet. Moreover, the automatically designed alphabets were compared against other reduced alphabets taken from the literature or human-designed, outperforming them. The differences between our alphabets and the alphabets taken from the literature were quantitatively analyzed. All the above process had been performed using a primary sequence representation of proteins. As a final experiment, we extrapolated the obtained five-letter alphabet to reduce a, much richer, protein representation based on evolutionary information for the prediction of the same two features. Again, the performance gap between the full representation and the reduced representation was small, showing that the results of our automated alphabet reduction protocol, even if they were obtained using a simple representation, are also able to capture the crucial information needed for state-of-the-art protein representations. Conclusion Our automated alphabet reduction protocol generates competent reduced alphabets tailored specifically for a variety of protein datasets. This process is done without any domain knowledge, using information theory metrics instead. The reduced alphabets contain some unexpected (but sound) groups of amino acids, thus suggesting new ways of interpreting the data.

Background Statistical analysis of DNA microarray data provides a valuable diagnostic tool for the investigation of genetic components of diseases. To take advantage of the multitude of available data sets and analysis methods, it is desirable to combine both different algorithms and data from different studies. Applying ensemble learning, consensus clustering and cross-study normalization methods for this purpose in an almost fully automated process and linking different analysis modules together under a single interface would simplify many microarray analysis tasks. Results We present ArrayMining.net, a web-application for microarray analysis that provides easy access to a wide choice of feature selection, clustering, prediction, gene set analysis and cross-study normalization methods. In contrast to other microarray-related web-tools, multiple algorithms and data sets for an analysis task can be combined using ensemble feature selection, ensemble prediction, consensus clustering and cross-platform data integration. By interlinking different analysis tools in a modular fashion, new exploratory routes become available, e.g. ensemble sample classification using features obtained from a gene set analysis and data from multiple studies. The analysis is further simplified by automatic parameter selection mechanisms and linkage to web tools and databases for functional annotation and literature mining. Conclusion ArrayMining.net is a free web-application for microarray analysis combining a broad choice of algorithms based on ensemble and consensus methods, using automatic parameter selection and integration with annotation databases.

International audience; This paper introduces mirrored sampling into evolution strategies (ESs) with weighted multi-recombination. Two further heuristics are introduced: pairwise selection selects at most one of two mirrored vectors in order to avoid a bias due to recombination. Selective mirroring only mirrors the worst solutions of the population. Convergence rates on the sphere function are derived that also yield upper bounds for the convergence rate on any spherical function. The optimal fraction of offspring to be mirrored is regardless of pairwise selection one without selective mirroring and about 19% with selective mirroring, where the convergence rate reaches a value of 0.390. This is an improvement of 56% compared to the best known convergence rate of 0.25 with positive recombination weights.

The population-based ant colony optimization algorithm (P-ACO) differs from other ACO algorithms through its implementation of the pheromone update management. P-ACO keeps track of a population of solutions, which serves as an archive of solutions generated by the ants’ colony. Pheromone updates in P-ACO are only done based on solutions that enter or leave the solution archive. The population-based scheme reduces considerably the computation time needed for the pheromone update when compared to ACO algorithms such as Ant System. In this work, we study P-ACO’s behavior for solving the traveling salesman problem and the quadratic assignment problem. In particular, we investigate the impact of a local search on P-ACO parameters and performance. The results clearly show that P-ACO is a very competitive tool in which its parameters and behavior depend strongly on the problem tackled and whether or not a local search is used.

The NK landscapes are a well known benchmark for genetic algorithms (GAs) in which it is possible to tune the ruggedness of the fitness landscape by simply modifying the value of a parameter K. They have successfully been used in many theoretical studies, allowing researchers to discover interesting properties of the GAs dynamics in presence of rugged landscapes. A similar benchmark does not exist for genetic programming (GP) yet. Nevertheless, during the EuroGP conference debates of the last few years, the necessity of defining new benchmark problems for GP has repeatedly been expressed by a large part of the attendees. This paper is intended to fill this gap, by introducing an extension of the NK landscapes to tree based GP, that we call K landscapes. In this benchmark, epistasis are expressed as growing mutual interactions between the substructures of a tree as the parameter K increases. The fact that the problem becomes more and more difficult as the value of K increases is experimentally demonstrated. Interestingly, we also show that GP "bloats" more and more as K increases. Copyright 2011 ACM

In this paper a method to increase the optimization ability of genetic algorithms (GAs) is proposed. To promote population diversity, a fraction of the worst individuals of the current population is replaced by individuals from an older population. To experimentally validate the approach we have used a set of well-known benchmark problems of tunable difficulty for GAs, including trap functions and NK landscapes. The obtained results show that the proposed method performs better than standard GAs without elitism for all the studied test problems and better than GAs with elitism for the majority of them.