The high cost of processor fabrication plants and approaching physical limits have started a new wave research in alternative computing paradigms. As an alternative to the top-down manufactured silicon-based computers, research in computing using natural and physical system directly has recently gained a great deal of interest. A branch of this research promotes the idea that any physical system with sufficiently complex dynamics is able to perform computation. The power of networks in representing complex interactions between many parts make them a suitable choice for modeling physical systems. Many studies used networks with a homogeneous structure to describe the computational circuits. However physical systems are inherently heterogeneous. We aim to study the effect of heterogeneity in the dynamics of physical systems that pertains to information processing. Two particularly well-studied network models that represent information processing in a wide range of physical systems are Random Boolean Networks (RBN), that are used to model gene interactions, and Liquid State Machines (LSM), that are used to model brain-like networks. In this thesis, we study the effects of function heterogeneity, in-degree heterogeneity, and interconnect irregularity on the dynamics and the performance of RBN and LSM. First, we introduce the model parameters to characterize the heterogeneity of components in RBN and LSM networks. We then quantify the effects of heterogeneity on the network dynamics. For the three heterogeneity aspects that we studied, we found that the effect of heterogeneity on RBN and LSM are very different. We find that in LSM the in-degree heterogeneity decreases the chaoticity in the network, whereas it increases chaoticity in RBN. For interconnect irregularity, heterogeneity decreases the chaoticity in LSM while its effects on RBN the dynamics depends on the connectivity. For {K} < 2, heterogeneity in the interconnect will increase the chaoticity in the dynamics and for {K} > 2 it decreases the chaoticity. We find that function heterogeneity has virtually no effect on the LSM dynamics. In RBN however, function heterogeneity actually makes the dynamics predictable as a function of connectivity and heterogeneity in the network structure. We hypothesize that node heterogeneity in RBN may help signal processing because of the variety of signal decomposition by different nodes.

[pt] Esta tese investiga a utilização de computação evolutiva aplicada à síntese de circuitos eletrônicos. A computação evolutiva compreende uma classe de algoritmos que utilizam certos aspectos da evolução natural como metáforas. Particularmente, a seleção natural, a recombinação de material genético e a mutação são os mecanismos biológicos nos quais a maior parte destes algoritmos evolutivos buscam inspiração. Embora algoritmos evolutivos tenham encontrado em problemas de otimização o seu maior potencial de aplicação, a utilização dos mesmos na síntese de circuitos eletrônicos vem sendo intensamente investigada nos últimos anos, dando início à área de pesquisa denominada de Eletrônica Evolutiva. Esta tese enfoca a área de eletrônica evolutiva sob o ponto de vista de engenharia de circuitos, e seu maior objetivo é oferecer embasamento teórico e experimental para proposta de novas ferramentas de Computer Aided Design (CAD) de circuitos eletrônicos. Nesta pesquisa, a utilização de algoritmos evolutivos não se restringiu àqueles que empregam apenas os três operadores genéticos descritos anteriormente, isto é, seleção, recombinação e mutação. Investigou-se a inclusão de novos métodos e operadores ao fluxo básico dos algoritmos evolutivos, com o propósito de melhorar seu desempenho em problemas na área de Eletrônica Evolutiva. Particularmente, estudou-se a utilização de complexidade através de sistemas com representação variável sistemas evolutivos que utilizem como metáfora o conceito biológico de especiação. Além disso, uma nova metodologia para otimização com múltiplos objetivos, baseada em conceitos de aprendizado de Redes Neurais Artificiais, for também concebida nessa tese. Realizou-se um amplo estudo de casos, abrangendo eletrônica analógica, digital e microeletrônica. Uma grande variedade de circuitos de caráter prático foi sintetizada, tais como: filtros, amplificadores, osciladores, retificadores, receptores, comparadores, multiplexadores e portas digitais básicas. Novos paradigmas de eletrônica evolutiva foram também concebidos, com o intuito de tornar os circuitos projetados competitivos com aqueles convencionalmente utilizados; estes paradigmas referem-se à forma como os circuitos são avaliados ao longo do algoritmo evolutivo. A plataforma para realização dos experimentos consistiu de simuladores de circuitos e também de circuitos integrados reconfiguráveis. Os resultados mostram que esta nova classe de ferramentas de CAD pode chegar a circuitos mais eficientes do que os obtidos por ferramentas convencionais. Além disso, circuitos eletrônicos sintetizados por computação evolutiva são em geral bastante distintos daqueles projetados convencionalmente, o que contribui para a concepção de novas metodologias de projeto. / [en] This thesis investigates the application of evolutionary computing techniques in the synthesis of electronic circuits. Evolutionary computation encompasses a particular class of algorithm which employ some aspects of natural evolution as metaphors. Particularly, most of these algorithms borrow ideas from the natural selection, genetic material recombination and mutation biological mechanisms. Even though evolutionary algorithms have been intensively investigates recently, starting a new research area called Evolutionary Electronics. This work focuses on evolutionary electronics from a enginnering perspective and the main objective is the proposal of a new generation of a Computer Aided Design (CAD) tools. Many case studies have been analysed, covering digital and analog microelectronics. The work aimed the achievement of competitive results comparing to other CAD tools. The research has made use of evolutionary algorithms tailored to these application, by including other genetic operators besides the ones defined above. The following methods have been embedded in the evolutionary methodology: memory based genetic algorithms, use of variable length representation systems and the use of the biological speciation metaphor. Furthermore, a new multiple-objective optimization method, based on artificial neural networks learning algorithms, has also been employed in the case studies. A large number of circuits of practical interest have been sysnthesised, such as filters, amplifiers, oscillators, rectifiers, receptors, comparators refer to new approaches for circuits evaluation, particularly in the digital domain. Circuit simulators and analog the reconfigurable circuits have been used as platforms for the evolutionary process. The results show that the circuits synthesided through evolutionary computation are, in some cases, more efficient than the human designed ones. Besides, the evolved circuits are usually quite different from their human designed counterparts, which can contribute to the creation of new design methodologies. The author identified many promising ways of evolutionary algorithms application in analog and digital design, which may, in the future, overcome conventional design in terms of area, speed and power consumption.

I present a new approach to evolutionary search called novelty search, wherein only behavioral novelty is rewarded, thereby abstracting evolution as a search for novel forms. This new approach contrasts with the traditional approach of rewarding progress towards the objective through an objective function. Although they are designed to light a path to the objective, objective functions can instead deceive search into converging to dead ends called local optima. As a significant problem in evolutionary computation, deception has inspired many techniques designed to mitigate it. However, nearly all such methods are still ultimately susceptible to deceptive local optima because they still measure progress with respect to the objective, which this dissertation will show is often a broken compass. Furthermore, although novelty search completely abandons the objective, it counterintuitively often outperforms methods that search directly for the objective in deceptive tasks and can induce evolutionary dynamics closer in spirit to natural evolution. The main contributions are to (1) introduce novelty search, an example of an effective search method that is not guided by actively measuring or encouraging objective progress; (2) validate novelty search by applying it to biped locomotion; (3) demonstrate novelty search’s benefits for evolvability (i.e. the ability of an organism to further evolve) in a variety of domains; (4) introduce an extension of novelty search called minimal criteria novelty search that brings a new abstraction of natural evolution to evolutionary computation (i.e. evolution as a search for many ways of iii meeting the minimal criteria of life); (5) present a second extension of novelty search called novelty search with local competition that abstracts evolution instead as a process driven towards diversity with competition playing a subservient role; and (6) evolve a diversity of functional virtual creatures in a single run as a culminating application of novelty search with local competition. Overall these contributions establish novelty search as an important new research direction for the field of evolutionary computation.

Layered learning is a machine learning paradigm used to develop autonomous robotic-based agents by decomposing a complex task into simpler subtasks and learns each sequentially. Although the paradigm continues to have success in multiple domains, performance can be unexpectedly unsatisfactory. Using Boolean-logic problems and autonomous agent navigation, we show poor performance is due to the learner forgetting how to perform earlier learned subtasks too quickly (favoring plasticity) or having difficulty learning new things (favoring stability). We demonstrate that this imbalance can hinder learning so that task performance is no better than that of a suboptimal learning technique, monolithic learning, which does not use decomposition. Through the resulting analyses, we have identified factors that can lead to imbalance and their negative effects, providing a deeper understanding of stability and plasticity in decomposition-based approaches, such as layered learning. To combat the negative effects of the imbalance, a complementary learning system is applied to layered learning. The new technique augments the original learning approach with dual storage region policies to preserve useful information from being removed from an agent’s policy prematurely. Through multi-agent experiments, a 28% task performance increase is obtained with the proposed augmentations over the original technique.

Feature extraction is one of the major challenges in object recognition. Features that are extracted from one type of objects cannot always be used directly for a different type of objects, therefore limiting the performance of feature extraction. Having an automatic feature learning algorithm could be a big advantage for an object recognition algorithm. This research first introduces several improvements on a fully automatic feature construction method called Evolution COnstructed Feature (ECO-Feature). These improvements are developed to construct more robust features and make the training process more efficient than the original version. The main weakness of the original ECO-Feature algorithm is that it is designed only for binary classification and cannot be directly applied to multi-class cases. We also observe that the recognition performance depends heavily on the size of the feature pool from which features can be selected and the ability of selecting the best features. For these reasons, we have developed an enhanced evolutionary learning method for multi-class object classification to address these challenges. Our method is called Evolutionary Learning of Boosted Features (ECO-Boost). ECO-Boost method is an efficient evolutionary learning algorithm developed to automatically construct highly discriminative image features from the training image for multi-class image classification. This unique method constructs image features that are often overlooked by humans, and is robust to minor image distortion and geometric transformations. We evaluate this algorithm with a few visual inspection datasets including specialty crops, fruits and road surface conditions. Results from extensive experiments confirm that ECO-Boost performs closely comparable to other methods and achieves a good balance between accuracy and simplicity for real-time multi-class object classification applications. It is a hardware-friendly algorithm that can be optimized for hardware implementation in an FPGA for real-time embedded visual inspection applications.

No description available.

<p dir="ltr">The concept of reinforcement learning has become increasingly relevant in learning- based applications, especially in the field of autonomous navigation, because of its fundamental nature to operate without the necessity of labeled data. However, the infeasibility of training reinforcement learning based autonomous navigation applications in a real-world setting has increased the popularity of researching and developing on autonomous navigation systems by creating simulated environments in game engine platforms. This thesis investigates the comparative performance of Unity and Unreal Engine 5 within the framework of a reinforcement learning system applied to autonomous race car navigation. A rudimentary simulated setting featuring a model car navigating a racetrack is developed, ensuring uniformity in environmental aspects across both Unity and Unreal Engine 5. The research employs reinforcement learning with genetic algorithms to instruct the model car in race track navigation; while the tools and programming methods for implementing reinforcement learning vary between the platforms, the fundamental concept of reinforcement learning via genetic algorithms remains consistent to facilitate meaningful comparisons. The implementation includes logging of key performance variables during run times on each platform. A comparative analysis of the performance data collected demonstrates Unreal Engine's superior performance across the collected variables. These findings contribute insights to the field of autonomous navigation systems development and reinforce the significance of choosing an optimal underlying simulation platform for reinforcement learning applications.</p>

No

Fuzzy association rule mining discovers patterns in transactions, such as shopping baskets in a supermarket, or Web page accesses by a visitor to a Web site. Temporal patterns can be present in fuzzy association rules because the underlying process generating the data can be dynamic. However, existing solutions may not discover all interesting patterns because of a previously unrecognised problem that is revealed in this thesis. The contextual meaning of fuzzy association rules changes because of the dynamic feature of data. The static fuzzy representation and traditional search method are inadequate. The Genetic Iterative Temporal Fuzzy Association Rule Mining (GITFARM) framework solves the problem by utilising flexible fuzzy representations from a fuzzy rule-based system (FRBS). The combination of temporal, fuzzy and itemset space was simultaneously searched with a genetic algorithm (GA) to overcome the problem. The framework transforms the dataset to a graph for efficiently searching the dataset. A choice of model in fuzzy representation provides a trade-off in usage between an approximate and descriptive model. A method for verifying the solution to the hypothesised problem was presented. The proposed GA-based solution was compared with a traditional approach that uses an exhaustive search method. It was shown how the GA-based solution discovered rules that the traditional approach did not. This shows that simultaneously searching for rules and membership functions with a GA is a suitable solution for mining temporal fuzzy association rules. So, in practice, more knowledge can be discovered for making well-informed decisions that would otherwise be lost with a traditional approach.

Thesis (MScEng (Process Engineering))--University of Stellenbosch, 2006. / The natural immune system is an exceptional pattern recognition system based on memory and learning that is capable of detecting both known and unknown pathogens. Artificial immune systems (AIS) employ some of the functionalities of the natural immune system in detecting change in dynamic process systems. The emerging field of artificial immune systems has enormous potential in the application of fault detection systems in process engineering. This thesis aims to firstly familiarise the reader with the various current methods in the field of fault detection and identification. Secondly, the notion of artificial immune systems is to be introduced and explained. Finally, this thesis aims to investigate the performance of AIS on data gathered from simulated case studies both with and without noise. Three different methods of generating detectors are used to monitor various different processes for anomalous events. These are: (1) Random Generation of detectors, (2) Convex Hulls, (3) The Hypercube Vertex Approach. It is found that random generation provides a reasonable rate of detection, while convex hulls fail to achieve the required objectives. The hypercube vertex method achieved the highest detection rate and lowest false alarm rate in all case studies. The hypercube vertex method originates from this project and is the recommended method for use with all real valued systems, with a small number of variables at least. It is found that, in some cases AIS are capable of perfect classification, where 100% of anomalous events are identified and no false alarms are generated. Noise has, expectedly so, some effect on the detection capability on all case studies. The computational cost of the various methods is compared, which concluded that the hypercube vertex method had a higher cost than other methods researched. This increased computational cost is however not exceeding reasonable confines therefore the hypercube vertex method nonetheless remains the chosen method. The thesis concludes with considering AIS’s performance in the comparative criteria for diagnostic methods. It is found that AIS compare well to current methods and that some of their limitations are indeed solved and their abilities surpassed in certain cases. Recommendations are made to future study in the field of AIS. Further the use of the Hypercube Vertex method is highly recommended in real valued scenarios such as Process Engineering.