Search

Artificial Intelligence harnessed from knowledge graphs and logical reasoning yields excellent interpretability as well as proficient reasoning and decision-making capabilities. Declarative rules, such as Prolog and Datalog, are prevalent formalisms for expressing expert knowledge and are employed in numerous systems due to their inherent explicability. This thesis introduces Evoda, a novel, evolutionary-based algorithm conceived for rule mining on large-scale knowledge graphs (KGs) and classification problems. While current methodologies examine the rule hypothesis space undertake exhaustive searches, subjected to heuristic and syntactic limitations on the rule language, thereby constraining the quality of the derived rules. In this research, the rule hypothesis space is broadened from conventional path rules to encompass general Datalog rules, with Evoda as a new metaheuristic genetic logic programming algorithm. Rule evaluation is extended from the restrictive closed world assumption (CWA) to a more practical open world assumption (OWA). Experimental results, assessed using various evaluation metrics on multiple real-world knowledge graphs, underscore Evoda's proficiency in mining superior quality rules, its enhanced precision in predictions within the enlarged rule space, and its significant strides in efficiency and scalability, handling up to 22 million facts within mere seconds. Additionally, we proposed and demonstrated that existential rules accelerate the learning rate through the inclusion of intermediate states. It surpasses several state-of-the-art rule mining and embedding models in KG completion tasks. From a machine learning standpoint, Evoda necessitates only a select few hyperparameters that display discernible patterns, thus obviating the need for hyperparameter tuning. Moreover, Evoda demonstrates exceptional performance on diverse classification datasets from academic to industry applications. In summary, this work accentuates the feasibility, effectiveness, and efficiency of the newly proposed evolutionary learning framework.

This paper presents a generative architecture for general-purpose room layouts that can be treated as geometric definitions of dungeons, mansions, shooter levels and more. The motivation behind this work is to provide a design tool for virtual environments that combines aspects of controllability, expressivity and generality. Towards that end, a two-tier level representation is realized, with a graph-based design specification constraining and guiding the generated geometries, facilitated by constrained evolutionary search. Expressivity is secured through quality-diversity search which can provide the designer with a broad variety of level layouts to choose from. Finally, the generator is general-purpose as it can produce layouts based on different types of static grid structures or as freeform, curved structures through an adaptive Voronoi diagram that is evolved along with the level itself. The method is tested on a variety of design specifications and grid types, and results show that even with complex design constraints or malleable grids the algorithm can produce a broad variety of levels., peer-reviewed

Evolutionary algorithms (EAs) have been with us for several decades and are highly popular given that they have proved competitive in the face of challenging problems’ features such as deceptiveness, multiple local optima, among other characteristics. However, it is necessary to define multiple hyper-parameter values to have a working EA, which is a drawback for many practitioners. In the case of genetic programming (GP), an EA for the evolution of models and programs, hyper-parameter optimization has been extensively studied only recently. This work builds on recent findings and explores the hyper-parameter space of a specific GP system called neat-GP that controls model size. This is conducted using two large sets of symbolic regression benchmark problems to evaluate system performance, while hyper-parameter optimization is carried out using three variants of the iterated F-Race algorithm, for the first time applied to GP. From all the automatic parametrizations produced by optimization process, several findings are drawn. Automatic parametrizations do not outperform the manual configuration in many cases, and overall, the differences are not substantial in terms of testing error. Moreover, finding parametrizations that produce highly accurate models that are also compact is not trivially done, at least if the hyper-parameter optimization process (F-Race) is only guided by predictive error. This work is intended to foster more research and scrutiny of hyper-parameters in EAs, in general, and GP, in particular.

Multi-objective evolutionary algorithms are widely used by researchers and practitioners to solve multi-objective optimization problems (MOPs), since they require minimal assumptions and are capable of computing a finite size approximation of the entire solution set in one run of the algorithm. So far, however, the adequate treatment of equality constraints has played a minor role. Equality constraints are particular since they typically reduce the dimension of the search space, which causes problems for stochastic search algorithms such as evolutionary strategies. In this paper, we show that multi-objective evolutionary algorithms hybridized with continuation-like techniques lead to fast and reliable numerical solvers. For this, we first propose three new problems with different characteristics that are indeed hard to solve by evolutionary algorithms. Next, we develop a variant of NSGA-II with a continuation method. We present numerical results on several equality-constrained MOPs to show that the resulting method is highly competitive to state-of-the-art evolutionary algorithms.

Scaling petaflop supercomputers to exascale requires a 500x increase in FLOPS, but at the cost of only a 3x increase in the total power consumption. In addition, computing systems implemented with nanometer scale multi-gate field effect transistors are increasingly integrating heterogeneous cores, GPUs, and accelerators. The power delivery and energy management of such complex chip multi-processors (CMP) is, therefore, a challenging research task spanning across the system, architecture, circuits, and device stack. A set of on-chip energy management techniques that are similar to supply side and demand side management in a SMART grid is developed. The techniques span the circuit and system layers. Intelligence is introduced in the operation of the on-chip power distribution network (PDN) to sense variations in the computational activity across cores and reconfigure the PDN to optimize the energy efficiency. A circuit level technique that improves the energy efficiency through the implementation of under-provisioned on-chip voltage regulators (OCVRs) interconnected through a switch network is developed. An operating system level task scheduling heuristic distributes the workloads on the cores such that the required reconfiguration of the PDN is minimized. SPICE simulations indicate up to a 44% reduction in the energy consumption of the CMP. An evolving on-chip power delivery methodology where reference voltages of the OCVRs are controlled through a particle swarm optimizer (PSO) is developed. The PSO negates the effects of transistor aging and process, temperature, and power supply noise induced variation in the load circuit, OCVRs, and on-chip timing sensors. The simulation results indicate an average reduction of 35% and 5% in, respectively, the power consumption and operating temperature of the voltage domains. In addition, the end of life of the voltage domain is prolonged due to a mean reduction in the aging induced Vth shift of 40%. Novel circuit techniques to detect and set the power supply voltages and suppress power supply noise are developed. The run-time circuit techniques for power supply voltage detection and clamping are demonstrated for a heterogeneous 3-D integrated circuit through SPICE simulation of a device plane in a 22 nm technology and a power plane in a 45 nm technology. The power supply voltages of less than 1 V are successfully set and provided as a reference to an OCVR within 500 ns of initiating an active state and with variation of less than 1% in the reference voltage. Noise on the power supply is suppressed through the use of hyperabrupt p-n junction varactors as on-chip decoupling capacitors. The voltage droops and overshoots on the on chip power distribution network are suppressed by up to 60% as compared to metal insulator metal (MIM) or deep trench decoupling capacitors of the same capacitance. With approximately 42% and 15% of the data center power consumed by, respectively, the processors and the cooling system, the run-time energy management techniques developed in this thesis have significant potential to reduce the running cost of exascale data centers.

Η παρούσα εργασία πραγματεύεται τον υπολογισμό της διδιάστατης ασυμπίεστης και ατριβούς ροής που διέρχεται μέσω μιας ατέρμονος πτερύγωσης σε μη μόνιμη κατάσταση. Για τον υπολογισμό χρησιμοποιείται η μέθοδος των ιδιόμορφων σημείων. Μετά την αναλυτική θεωρητική περιγραφή της μεθόδου ακολουθεί και η περιγραφή του προγράμματος Η/Υ σε γλώσσα FORTRAN, με το οποίο έγιναν οι υπολογισμοί. Τα αριθμητικά αποτελέσματα συγκρίνονται με αντίστοιχα αποτελέσματα άλλων ερευνητών. Η μέθοδος επεκτείνεται στα τελευταία κεφάλαια για να υπολογίσει τη ροή που διέρχεται μέσα από δυο διαδοχικές ατέρμονες πτερυγώσεις σε μη μόνιμη κατάσταση όπου δίνεται η απαραίτητη θεωρητική ανάλυση και περιγράφεται το αντίστοιχο πρόγραμμα Η/Υ.

Includes bibliography (p. 165-181). Thesis (Ph. D.) -- University of Cyprus, Faculty of Pure and Applied Sciences,Department of Computer Science, June 2010. The University of Cyprus Library holds the printed form of the thesis. Number of sources in the bibliography: 128 Ο Σχεδιασμός Βέλτιστου Γραφήματος (ΣΒΓ) είναι ένα κοινό πρόβλημα που συναντάτε σε ποικίλα ερευνητικά πεδία όπως τον σχεδιασμό δικτύων επικοινωνιών και συγκοινωνιών, και την ανακάλυψη νέων φαρμάκων. Συχνά τα γραφήματα που σχεδιάζονται πρέπει να ικανοποιούν πολλαπλούς, αντικρουόμενους στόχους (κριτήρια) όπως το συνολικό μήκος, την πολυπλοκότητα ή άλλους περιορισμούς σχετικούς με το σχήμα και τις ιδιότητες τους. Επιπρόσθετα από τα κριτήρια που σχετίζονται με το συγκεκριμένο πρόβλημα, οι μέθοδοι επίλυσης του προβλήματος επιβάλλεται όπως λαμβάνουν υπόψη θέματα που αφορούν την αναπαράσταση των προτεινόμενων λύσεων και την διαχείριση γραφημάτων. Αυτά τα θέματα, σε συνδυασμό με την πολυκριτηριακή φύση του προβλήματος ΣΒΓ, διαμορφώνουν ένα προκλητικό πρόβλημα με αυξημένη πολυπλοκότητα και ευρύ πεδίο εφαρμογών σε πολλές ερευνητικές κατευθύνσεις. Η έρευνά μας προτείνει το MEGA, ένα αλγοριθμικό πλαίσιο για την επίλυση του προβλήματος του σχεδιασμού βέλτιστου γραφήματος πολλαπλών στόχων (πολυκριτηριακού) για μη κατευθυνόμενα γραφήματα με ονομαστικές ακμές και κόμβους. Η μέθοδος χρησιμοποιεί πολυκριτηριακά εξελικτικά γραφήματα, μια μετά-ευριστική τεχνική βελτιστοποίησης που συνδυάζει τους εξελικτικούς αλγορίθμους με τη θεωρία γράφων και με τοπικές τεχνικές αναζήτησης που αξιοποιούν συγκεκριμένους τομείς γνώσης, για να διερευνήσει αποτελεσματικά τον εφικτό χώρο αναζήτησης και να παράξει πολλαπλές ισοδύναμες συμβιβαστικές λύσεις. Ο αλγόριθμος εισάγει ένα καινοτόμο μηχανισμό διατήρησης της πολυμορφίας των λύσεων που λαμβάνει υπόψη τόσο τον παραμετρικό όσο και τον χώρο των λύσεων. Επιπρόσθετα, η μέθοδος χρησιμοποιεί μια αυτοπροσαρμοζόμενη προσέγγιση για να ελέγχει και εξασφαλίζει την κατάλληλη χρήση της τεχνικής τοπικής αναζήτησης. Στην πειραματική ενότητα παρουσιάζονται τα αποτελέσματα για το πρόβλημα του σχεδιασμού μοριακών δομών που ικανοποιούν πολλαπλούς στόχους με φαρμακευτικό ενδιαφέρον. Τα αποτελέσματα δείχνουν ότι η μέθοδος είναι ικανή να προσφέρει μια ποικιλία από έγκυρες, ενδιαφέρουσες λύσεις σε μορφή γραφημάτων. Σε σύγκριση με αλγόριθμους που χρησιμοποιούνται ευρέως, το MEGA παράγει στατιστικά σημαντικά καλύτερα αποτελέσματα τα οποία περιγράφονται αναλυτικά. Optimal Graph Design is a problem frequently occurring in several common applications ranging from designing communication and transportation networks to discovering new drugs. More often than not the graphs to be designed need to satisfy multiple, conflicting, objectives e.g. total length, complexity or other shape and property limitations. In addition to problem specific criteria, the methods proposed to solve the problem need to consider several issues related to the representation of the solutions and the manipulation of graphs. These graph-structure specific issues coupled with the multi-objective nature of applied OGD form a challenging problem of increased complexity with wide applications in several research fields. Our research proposes, MEGA, an algorithmic framework for solving the problem of multi-objective optimal graph design for labeled, undirected graphs. The method uses multi-objective evolutionary graphs, a graph-specific meta-heuristic optimization technique that combines evolutionary algorithms with graph theory and local search techniques exploiting domain-specific knowledge, to efficiently explore the feasible search space and obtain multiple equivalent compromising solutions. The algorithm introduces a novel niching mechanism that takes into account both parameter and objective space solution diversity. Moreover, the method implements a self-adaptive approach to control and ensure appropriate local search use. In the experimental section we present results for the problem of designing molecules satisfying multiple pharmaceutically relevant objectives. The results suggest that the method can provide a variety of valid, interesting graph solutions. In comparisons with commonly used algorithms, MEGA is found to produce statistically significant better results.

Includes bibliographical references (p. 193-194) and index. Number of sources in the bibliography: 193 Thesis (Ph. D.) -- University of Cyprus, Faculty of Pure and Applied Sciences, Department of Computer Science, February 2009. The University of Cyprus Library holds the printed form of the thesis. Ο κύριος στόχος της διατριβής είναι η ανάπτυξη ενός πλαισίου για τη δημιουργία μιας νέας κατηγορίας Ευφυών Συστημάτων Λήψης Απόφασης, τα οποία θα έχουν εφαρμογή σε πολύπλοκα προβλήματα που κινούνται σε ένα περιβάλλον αβεβαιότητας, με παράλληλη δυνατότητα πρόβλεψης. Οι Ασαφείς Γνωστικοί Χάρτες (ΑΓΧ) είναι μια εναλλακτική προσέγγιση η οποία αυξάνει τις δυνατότητες των Συστημάτων Λήψης Απόφασης και των Έμπειρων Συστημάτων. Πιο συγκεκριμένα η μεθοδολογία βασίζεται στην κωδικοποίηση της γνώσης των εμπειρογνωμόνων και της κρίσης τους σε μία εξειδικευμένη Ασαφή Γνωστική Βάση ειδικά σχεδιασμένη να χειρίζεται πολύπλοκες γλωσσικές μεταβλητές. Η γνώση αυτή μοντελοποιείται και τυγχάνει επεξεργασίας με τη χρήση των ΑΓΧ, οι οποίοι έχουν δύο σημαντικές αδυναμίες. Η πρώτη αφορά στο ότι τα βάρη που συμμετέχουν στη διαμόρφωση ενός προβλήματος παραμένουν αμετάβλητα καθ΄ όλη τη διάρκεια της εκτέλεσης του υπολογιστικού μέρους ενός μοντέλου, πράγμα που περιορίζει τις δυνατότητες μελέτης και ανάλυσης προβλημάτων από τον πραγματικό κόσμο. Η δεύτερη αδυναμία της μεθόδου βρίσκεται στη δύσκολη και επίπονη (έως ανέφικτη) μοντελοποίηση καταστάσεων με ταυτόχρονη εκτέλεση όλων των πιθανών σεναρίων μετά την αλλαγή κάποιου βάρους ή μίας ομάδας βαρών. Οι δύο αυτές σημαντικές αδυναμίες έχουν αντιμετωπισθεί με το συνδυασμό των FCM και των Γενετικών Αλγορίθμων (ΓΑ) δημιουργώντας έτσι ένα Υβριδικό Εξελικτικό Ασαφές Γνωστικό Μοντέλο. Ακόμη δύο σημαντικές βελτιώσεις της θεωρίας των ΑΓΧ έχουν επίσης προταθεί σ΄ αυτή τη διδακτορική διατριβή. Η πρώτη αφορά στο χειρισμό του φαινομένου του Κύκλου Περιορισμένης Ταλάντωσης, ενώ η δεύτερη εισηγείται μια νέα προσέγγιση η οποία ονομάζεται Πολυεπίπεδη Δομή Ασαφών Γνωστικών Χαρτών, και στοχεύει στην ανάπτυξη συστημάτων τα οποία εμπεριέχουν πλήθος παραγόντων που αναλύονται σε επίπεδα υποπαραγόντων που συνδέονται με πολύπλοκες σχέσεις. Η μεθοδολογία έχει εφαρμοστεί επιτυχώς στην πράξη όπου διάφορα πραγματικά προβλήματα (επίλυση Κυπριακού προβλήματος) έχουν μοντελοποιηθεί, κυρίως στην περιοχή της διαχείρισης κρίσεων, λήψης πολιτικών αποφάσεων και καθορισμού στρατηγικής. Η εφαρμογή της προτεινόμενης μεθοδολογίας δεν περιορίζεται μόνο σε προβλήματα διαχείρισης κρίσεων αλλά μπορεί να επεκταθεί χωρίς σημαντικούς περιορισμούς και σε άλλες περιοχές λόγω της γενικής της φύσης, της απλότητάς της και των ξεκάθαρων σταδίων εφαρμογής της. The main goal of this research is the development of an innovative Intelligent Decision Support System within the framework of Genetically Evolved Fuzzy Cognitive Maps. It is intended for the modelling of real world problems and the supporting of decision making processes. Specifically, the proposed framework is based on encoding experts’ assessments on the nature of a crisis under consideration. This assessment is then inputted in a fuzzy knowledge base that uses a linguistic form which it is modelled and processed by means of a Fuzzy Cognitive Map (FCM). FCMs are an alternative approach to decision making processes as they expand the capabilities of Decision Support Systems (DSS) and Expert Systems (ES) and also support scenario analysis and forecasting. During this research, several drawbacks of FCMs were identified and addressed. The first involves the invariability of the weights that participate in the configuration of a given problem. The second lies within the inability of the method to model a certain situation by performing all possible computational simulations following the change of a certain weight or group of weights. We addressed this issue by combining FCMs with Genetic Algorithms (GA), thus creating Hybrid Evolutionary Fuzzy Cognitive Map models. Another two important improvements to the FCM theory were also proposed in the present thesis. The first concerns the handling of the “Limit Cycle phenomenon” attempting to improve the inference procedure, while the second improvement refers to the use of a new structured approach named Multilayered Fuzzy Cognitive Maps for the development of FCM-based systems that are able to handle large-scale, complex systems. The methodology was successfully applied in practice where several real world problems were modelled using the proposed framework, based mostly on the fields of crisis management, political decision-making and strategy definition. The effectiveness and reliability of the method proposed has been demonstrated by means of case studies in a number of problems related to the Cyprus issue. The application of the proposed methodology is not limited only to political or crisis management problems but can be further extended, without any restrictions, to other domains due to its generic nature and simple and straightforward steps.

Includes bibliography (p. 165-181). Thesis (Ph. D.) -- University of Cyprus, Faculty of Pure and Applied Sciences,Department of Computer Science, June 2010. The University of Cyprus Library holds the printed form of the thesis. Number of sources in the bibliography: 128 Επιπλέον, αξιοποιούμε τις προτεινόμενες μεθόδους για την επίλυση ενός πρακτικού ζητήματος. Συγκεκριμένα, αναπτύσσουμε ένα σύστημα το οποίο προσφέρει αξιόπιστες συστάσεις (recommendations) σε ευρωπαϊκούς οργανισμούς για καινούριες συνεργασίες. Για να το επιτύχουμε αυτό ομαδοποιούμε τους οργανισμούς που έχουν συμμετάσχει σε έργα που χρηματοδοτήθηκαν από την Ευρωπαϊκή Ένωση στο πλαίσιο του προγράμματος Horizon 2020. Στην συνέχεια, προτείνουμε μια μέθοδο που αναλύει τα αποτελέσματα της ομαδοποίησης για να εξάγει πιθανές συνεργασίες. Οι οργανισμοί και οι ερευνητές μπορούν να χρησιμοποιήσουν το σύστημά μας για να για να εντοπίσουν νέους συνεργάτες. Από όσο γνωρίζουμε, το σύστημα μας είναι το πρώτο που προσφέρει τέτοιες υπηρεσίες στην κοινότητα. Optimal Graph Design is a problem frequently occurring in several common applications ranging from designing communication and transportation networks to discovering new drugs. More often than not the graphs to be designed need to satisfy multiple, conflicting, objectives e.g. total length, complexity or other shape and property limitations. In addition to problem specific criteria, the methods proposed to solve the problem need to consider several issues related to the representation of the solutions and the manipulation of graphs. These graph-structure specific issues coupled with the multi-objective nature of applied OGD form a challenging problem of increased complexity with wide applications in several research fields. Our research proposes, MEGA, an algorithmic framework for solving the problem of multi-objective optimal graph design for labeled, undirected graphs. The method uses multi-objective evolutionary graphs, a graph-specific meta-heuristic optimization technique that combines evolutionary algorithms with graph theory and local search techniques exploiting domain-specific knowledge, to efficiently explore the feasible search space and obtain multiple equivalent compromising solutions. The algorithm introduces a novel niching mechanism that takes into account both parameter and objective space solution diversity. Moreover, the method implements a self-adaptive approach to control and ensure appropriate local search use. In the experimental section we present results for the problem of designing molecules satisfying multiple pharmaceutically relevant objectives. The results suggest that the method can provide a variety of valid, interesting graph solutions. In comparisons with commonly used algorithms, MEGA is found to produce statistically significant better results.

Thesis (PhDInformationTechnology)--University of South Australia, 2010 Membrane computing investigates models of computation inspired by certainfeatures of biological cells, especially features arising because of the presence ofmembranes. Because of their inherent large-scale parallelism, membrane computingmodels (called P systems) can be fully exploited only through the useof a parallel computing platform. However, it is an open question whether it isfeasible to develop an efficient and useful parallel computing platform for membranecomputing applications. Such a computing platform would significantlyoutperform equivalent sequential computing platforms while still achieving acceptablescalability, flexibility and extensibility. To move closer to an answer tothis question, I have investigated a novel approach to the development of a parallelcomputing platform for membrane computing applications that has the potentialto deliver a good balance between performance, flexibility, scalability andextensibility. This approach involves the use of reconfigurable hardware and anintelligent software component that is able to configure the hardware to suit thespecific properties of the P system to be executed. As part of my investigations,I have created a prototype computing platform called Reconfig-P based on theproposed development approach. Reconfig-P is the only existing computing platformfor membrane computing applications able to support both system-leveland region-level parallelism. Using an intelligent hardware source code generatorcalled P Builder, Reconfig-P is able to realise an input P system as a hardwarecircuit in various ways, depending on which aspects of P systems the user wishesto emphasise at the implementation level. For example, Reconfig-P can realisea P system in a rule-oriented manner or in a region-oriented manner. P Builderprovides a unified implementation framework within which the various implementationstrategies can be supported. The basic principles of this frameworkconform to a novel design pattern called Content-Form-Strategy. The framework seamlessly integrates the currently supported implementation approaches, andfacilitates the inclusion of additional implementation strategies and additional Psystem features. Theoretical and empirical results regarding the execution timeperformance and hardware resource consumption of Reconfig-P suggest that theproposed development approach is a viable means of attaining a good balancebetween performance, scalability, flexibility and extensibility. Most of the existingcomputing platforms for membrane computing applications fail to supportnondeterministic object distribution, a key aspect of P systems that presentsseveral interesting implementation challenges. I have devised an efficient algorithmfor nondeterministic object distribution that is suitable for implementationin hardware. Experimental results suggest that this algorithm could beincorporated into Reconfig-P without too significantly reducing its performanceor efficiency.

Includes bibliographical references (p. 193-194) and index. Number of sources in the bibliography: 193 Thesis (Ph. D.) -- University of Cyprus, Faculty of Pure and Applied Sciences, Department of Computer Science, February 2009. The University of Cyprus Library holds the printed form of the thesis. Πολλές υπάρχουσες μέθοδοι ομαδοποίησης αντικειμένων/κόμβων σε γράφους ιδιοτήτων θεωρούν ότι οι ιδιότητες των αντικειμένων είναι το ίδιο σημαντικές ή αγνοούν την ύπαρξη συνδέσεων πολλαπλών τύπων. Επίσης, ανακαλύπτουν ομάδες που χαρακτηρίζονται από ομοιογένεια χαρακτηριστικών και είναι πυκνά συνδεδεμένες (densely connected components). Ωστόσο, η αναγνώριση ομάδων αντικειμένων που μοιράζονται παρόμοιες συνδέσεις είναι επίσης σημαντική. The main goal of this research is the development of an innovative Intelligent Decision Support System within the framework of Genetically Evolved Fuzzy Cognitive Maps. It is intended for the modelling of real world problems and the supporting of decision making processes. Specifically, the proposed framework is based on encoding experts’ assessments on the nature of a crisis under consideration. This assessment is then inputted in a fuzzy knowledge base that uses a linguistic form which it is modelled and processed by means of a Fuzzy Cognitive Map (FCM). FCMs are an alternative approach to decision making processes as they expand the capabilities of Decision Support Systems (DSS) and Expert Systems (ES) and also support scenario analysis and forecasting. During this research, several drawbacks of FCMs were identified and addressed. The first involves the invariability of the weights that participate in the configuration of a given problem. The second lies within the inability of the method to model a certain situation by performing all possible computational simulations following the change of a certain weight or group of weights. We addressed this issue by combining FCMs with Genetic Algorithms (GA), thus creating Hybrid Evolutionary Fuzzy Cognitive Map models. Another two important improvements to the FCM theory were also proposed in the present thesis. The first concerns the handling of the “Limit Cycle phenomenon” attempting to improve the inference procedure, while the second improvement refers to the use of a new structured approach named Multilayered Fuzzy Cognitive Maps for the development of FCM-based systems that are able to handle large-scale, complex systems. The methodology was successfully applied in practice where several real world problems were modelled using the proposed framework, based mostly on the fields of crisis management, political decision-making and strategy definition. The effectiveness and reliability of the method proposed has been demonstrated by means of case studies in a number of problems related to the Cyprus issue. The application of the proposed methodology is not limited only to political or crisis management problems but can be further extended, without any restrictions, to other domains due to its generic nature and simple and straightforward steps.

The evolutionary nature of humans requires agent systems to be continuously replaced due to their inability to meet or adapt to our changing needs. Therefore, to eliminate the need for a human to continuously adapt an agent, evolutionary agents are required [Chu04, Ore99, Rak02, Syc96]. This dissertation develops a feasible option to ensuring that agents continuously develop desirable behaviour. The solution is a specialized architecture that embeds self-evolvement into a target agent. The specialized architecture ensures that desirable behaviour emerges from any agent, as it is embedded between the target agent and the target agent’s environment and therefore is able to obtain domain- and hardwarespecific information from the target agent. The specialized architecture is a comprehensive methodology that incorporates all agents with the ability to embed the required self-evolvement enhancements as domain- and hardwarespecific information is obtained from the target agent. The specialized architecture responsible for embedding self-evolvement into an agent is the generic self-evolvement effecting evolutionary agent (GSEEA). The GSEEA is developed with a single goal, which is to ensure that the target agent meets the requirements of a changing environment. Changing environmental conditions can include different network conditions and different platforms. The GSEEA’s goal is accomplished by embedding the required self-evolvement enhancements into the target agent to produce a self-evolvement enhanced agent. In this dissertation the GSEEA is implemented to demonstrate its feasibility and problem-solving accuracy. In the GSEEA implementation the target agent is a puzzle-solving agent and the self-evolvement enhanced agent is the selfevolvement enhanced puzzle-solving agent. The GSEEA’s deliberative component consists of two algorithms, namely a genetic algorithm and a learning algorithm. The GSEEA’s genetic algorithm develops knowledge base rules (selfContents III evolvement enhancements) that modify actuator information. The GSEEA’s learning algorithm updates developed knowledge base rules by modifying sensor information. The GSEEA tests the developed self-evolvement enhancements by embedding them into the target agent through the target agent’s knowledge base manager, evaluating the developed self-evolvement enhancements and deleting those which do not enhance the target agent. The target agent achieves selfevolvement as additional enhancements required by the self-evolvement enhanced agent can be achieved by applying the same process followed to enhance the target agent which was discussed previously. The evaluation of the GSEEA implementation demonstrated that the GSEEA was implemented successfully based on feasibility and problem-solving accuracy as the self-evolvement enhanced puzzle-solver agent outperformed the puzzlesolver agent. Prof. E.M. Ehlers

Tez (Yüksek Lisans) -- İstanbul Teknik Üniversitesi, Bilişim Enstitüsü, 2006, Thesis (M.Sc.) -- İstanbul Technical University, Institute of Informatics, 2006, Gösterilimlerin evrimsel algoritmalar üzerindeki etkisi durağan ortamlar için bugüne kadar birçok çalışmada incelenmiş, bununla beraber dinamik ortamlardaki etkisi ihmal edilmiştir. Bu çalışmada, farklı gösterilimlerin dinamik ortamlardaki etkisini deneysel olarak inceledik. Probleme ara dönüşüm olmaksızın çözüm olabilen gösterilimlere, dogrudan gösterilimler denir. Dolaylı gösterilimlerde ise, arama farklı bir uzayda yapıldığından dolayı, çözümün doğrudan gösterilim haline ulaşmak için bir dönüşüm gerekir. Genelde, doğrudan gösterilimler tüm uzayda arama yaptıklarından dolayı geçersiz çözümlerle de evrim sırasında baş etmelidir. Dolaylı gösterilimler genetik arama uzayında arama yaptığı ve aday çözümler genelde geçerli çözüm uzayına izdüştüğü için, geçersiz çözüm problemi yoktur. Testlerde çoğunluk tarafından bilinen çok boyutlu sırt çantası (multi- dimensional knapsack problem) ve gezgin satıcı (traveling salesman) optimizasyon problemleri için doğrudan ve dolaylı yöntemleri inceledik, ve karşılaştırdık. Çok boyutlu sırt çantası problemi için seçtiğimiz dolaylı ağırlık kodlama (weight coding) yöntemi ile travelling salesman problemi için kullandığımız dolaylı ötelenmis koordinatlar (perturbed coordinates) yöntemi, çözümü bulmak için temelde aynı mantığı paylaşıyor. Her iki yöntemde de aday çözümler, orjinal problemin bazı değerlerini değiştirerek biraz farklı bir problem elde ediyor. Daha sonra elde edilen yeni probleme hızlı bir sezgisel yöntemle çözüm buluyor. Bulunan bu çözümü de orjinal problemin çözümüymüş gibi kullanıyor.Dolaylı gösterilimlerde, her değişim anında, toplumu oluşturan çözümlerin genetik arama uzayındaki bileşenleri, çözüm uzayına izdüşürülerek, toplumun yeni probleme adapte olması sağlanıyor. Sonuçlar dolaylı gösterilimlerin değişim anlarında, sahip oldukları sezgisel adaptasyon mekanizmasıyla var olan çözümleri yeni probleme adapte etmelerinden dolayı dinamik problemler için daha uygun olduğunu gösterdi. Ek olarak, gösterilimlerin dinamik ortamlardaki etkisinin, statik ortamlardakinden daha büyük olduğunu gördük. Bu nedenle dinamik ortamlarda gösterilimler seçilirken seçici olunmalı, adaptif yöntemler tercih edilmelidir., The effect of different representations has been thoroughly analyzed for evolutionary algorithms in stationary environments. However, the role of representations in dynamic environments has been largely neglected so far. In this study, we empirically analyze the effects of different representations in dynamic environments. A representation is called direct, if it can be interpreted directly as a solution to the problem. In indirect representations, search is done in a different space, so mapping is required to get the direct representation of the solution. Direct representations do search in the entire search space, so generally method should deal with the infeasible solutions through evolution. In indirect representations, search is done in genetic search space and generally they all map to feasible solutions of the search space. Thus indirect representation do not have a problem of infeasible solutions. In tests, we analyzed and compared, direct and indirect representations for both generally known optimization problems, multi-dimensional knapsack problem and traveling salesman problem. Two indirect representations selected, weight coding for multi-dimensional knapsack problem and perturbed coordinates for traveling salesman problem, keep the same track while finding the solution. In both approaches, candidate solutions first creates a slightly changed problem, by changing some values of the original problem. Then they find a solution to the changed problem using a fast heuristic. In indirect representations, at each change point, existing population is adapted to the new problem by mapping solutions' components of genetic search space to solution space. Our results indicate that indirect representations are particularly suitable for dynamic problems, because they implicitly provide a heuristic adaptation mechanism that improves the current solutions after a change. In addition, we saw that the choice of representation in dynamic environments is even more important than in static environments. For this reason, you should be selective while deciding representation to be used in a dynamic environment and you should prefer adaptive representations., Yüksek Lisans, M.Sc.

In the 1990s, there was a sudden growth in the research and application of optimisation techniques based on the tenets of Darwinian evolution, leading to the establishment of the recognised field of Evolutionary Computation (EC). Of the main EC methods that exist, the Genetic Algorithm (GA) remains as one of the most successful and often used methods. The growth and success of the GA in other fields of engineering research suggested an attractive new paradigm wherein structures could be evolved from a basic design or structural universe to an optimum form. In practice, the GA has had significant success in the size and topology optimisation of discrete truss structures. This level of research and success however, has not translated to the sub-field of continuum structural optimisation. Efforts to this end have been limited and known GA-based methods either generate results of poor quality or are limited in terms of their applicability. This thesis is primarily concerned with establishing a GA as an effective and efficient method for the optimisation of two-dimensional continuum structures. For shape optimisation, a new binary GA search method was created that operates on the simplified search space of discrete boundary steps. The success of the new method in generating high quality solutions was validated through applications to a number of examples. Further developments of the GA-based shape optimisation method include the introduction, improvement and integration of the Fixed Grid (FG) method of structural analysis. The FG method provides an efficient means of disassociating the structural boundary from meshing constraints as well as provides an efficient means of generating structural response values. The merging of the FG and GA concepts created a powerful framework for the solution of two-dimensional shape optimisation problems. Examples show that the hybrid method is a highly applicable and effective means of generating optimal shapes. Having established the FGGA method, efforts were directed to increasing the overall efficiency. The result was a set of knowledge-based algorithms that were successful in reducing the computational effort required to achieve the optimum. The GA originally operated on an intuitively derived displacement-based fitness function. An analytical and computational investigation of the fitness function revealed a relationship to classical compliance based design. The shape optimisation method was also extended to include stress uniformity considerations though the introduction of a stress-based fitness function. Comparisons with well-established analytical optimums showed that the method is effective in generating highly accurate solutions. Finally, a new GA-based method for the topology optimisation of continuum structures through the simultaneous use of multiple genetic algorithms was introduced. As the first GA creates an optimal shape, the second GA creates an optimal topology by generating and removing holes within the structure, in response to the changing boundary shape. Beyond the original use of simultaneous genetic algorithms for the solution of the topology optimisation problem, the method is characterised by the use of structural response information in the form of iso-lines to guide the GA in creating an optimal topology. Computational applications and comparisons of the results showed that the method is effective in generating high fidelity solutions with smooth boundaries.

A new evolutionary design tool is presented, which uses shape grammars and a grammar-based form of evolutionary computation, grammatical evolution (GE). Shape grammars allow the user to specify possible forms, and GE allows forms to be iteratively selected, recombined and mutated: this is shown to be a powerful combination of techniques. The potential of GE and shape grammars for evolutionary design is examined by attempting to design a single-person shelter to be evaluated by collaborators from the University College Dublin School of Architecture, Landscape, and Engineering. The team was able to successfully generate conceptual shelter designs based on scrutiny from the collaborators. A number of avenues for future work are highlighted arising from the case study. Science Foundation Ireland Irish Research Council for Science, Engineering and Technology 6 months embargo - could not locate month of publication: publish in December to be safe? - AV 29/10/2010 ti, ke, published in April 24th according to http://www.ingentaconnect.com/content/ind/ijde/2010/00000003/00000001/art00001;jsessionid=hlwhjx5unv57.alexandra - AS 04/11/2010

Περίληψη: Εισαγωγή -- 2. Μέθοδοι μονοκριτήριας βελτιστοποίησης -- 3. Πολυκριτήρια βελτιστοποίηση -- 4. Η μέθοδος S.E.A.D.O. -- 5. Μοντελοποίηση στροβίλου αξονικής ροής -- 6. Ανάπτυξη ΕΑ για την βελτιστοποίηση πολυκριτήριων προβλημάτων -- 7. Συμπεράσματα

Περίληψη: Μη διαθέσιμο

Περίληψη: Μη διαθέσιμο

RESUMEN: En el campo de la Inteligencia Artificial se han propuesto técnicas en tres tipos básicos de aprendizaje: el aprendizaje supervisado, el aprendizaje no supervisado y el aprendizaje por refuerzo. Las implementaciones que se hacen de estas técnicas están enfocadas en su mayoría a un aprendizaje computacional que poca interacción tiene con el humano; es un aprendizaje que se compara con experiencias anteriores pero no se logra a partir de la propia interacción máquina-humano. Evol-PlayMac surge, entonces, como un sistema que trata en lo posible de solucionar este problema al tratarse de un desarrollo que tiene implementada una técnica de aprendizaje del área de la computación evolutiva, que permite que a través de un juego tradicional de tablero, el parqués, la máquina formule estrategias de juego que cada vez demuestren un mejor desempeño obteniendo un nivel de ganancia mayor y logrando esto a partir de la competencia contra un humano.

Περίληψη: φ. 1: Παράλληλοι εξελικτικοί αλγόριθμοι -- Κεφ. 2: Παράλληλη επεξεργασία -- Κεφ. 3: Παράλληλοι διαφορικοί εξελικτικοί -- Κεφ. 4: Ένας απλός παράλληλος διαφορικός εξελικτικός αλγόριθμος -- Κεφ. 5: Παράλληλος διαφορικός εξελικτικός αλγόριθμος με χρήση του πρότυπου MPI