A evolução de redes neurais artificiais encontra aplicações em diversos campos na área de aprendizado de máquina, em particular, simulações de vida artificial onde uma população de indivíduos controlados por redes neurais se adaptam num ambiente virtual a fim de realizar uma determinada tarefa. Similar ao processo natural pelo qual o comportamento do organismo se modifica filogeneticamente através da complexificação do sistema nervoso, tais simulações oferecem uma nova abordagem sintética no estudo da inteligência, em contraposição aos métodos simbólicos tradicionais. Um recente método, conhecido por NEAT (NeuroEvolution of Augmenting Topologies), é capaz de obter os pesos e a própria topologia de rede neural utilizando algoritmos genéticos. A codificação utilizada pelo NEAT é flexível o suficiente para permitir evolução aberta e arquiteturas neurais arbitrárias. Este trabalho apresenta uma implementação do NEAT que pode ser utilizada em conjunto com um simulador de propósito geral, chamado Breve, formando uma plataforma para experimentos de vida artificial. A implementação proposta também estende o NEAT para lidar com redes neurais dinâmicas, onde o nível de ativação dos neurônios varia continuamente no tempo. Este novo modelo é comparado com o método tradicional numa tarefa clássica de controle não-supervisionado, mostrando um aumento de eficiência na busca pela solução do problema. Os resultados obtidos motivam o uso desta plataforma para experimentos de vida artificial, onde uma população de indivíduos interage continuamente com um ambiente dinâmico, se adaptando ao longo das gerações. / The evolution of artificial neural networks has a wide range of applicability in diverse areas in the field of machine learning, particularly, in artificial life simulations where a population of individuals, controlled by neural networks, adapts in a virtual environment in order to solve a given task. Resembling the natural process in which an organism\'s behavior is subjected to phylogenetic modifications through the complexification of the nervous system, such simulations offer a new synthetic approach in the investigation of intelligence, counter posing traditional symbolic methods. A recent method known as NEAT (NeuroEvolution of Augmenting Topologies), is able to obtain the synaptic weights and the topology with the aid of genetic algorithms. The encoding used by NEAT is flexible enough to allow for open-ended evolution and arbitrary neural architectures. This work presents a NEAT implementation especially suitable to be used with a general purpose simulator known as Breve, constituting a framework for artificial life experiments. The proposed implementation extends NEAT to include dynamical neuron models, where their inner state continuously varies over time. The new model is then compared to the traditional method in a classic unsupervised control benchmark task, showing an efficiency increase while solving the problem. The obtained results motivate the proposed framework for general experiments in artificial life, in which a population of individuals continuously interact with a dynamical environment, adapting through generations.

Submitted by Filipe dos Santos (fsantos@pucsp.br) on 2018-11-28T09:10:13Z No. of bitstreams: 1 Carlos Eduardo Pires de Camargo.pdf: 6898896 bytes, checksum: a6aa82547faa73c068f21441da9ce364 (MD5) / Made available in DSpace on 2018-11-28T09:10:13Z (GMT). No. of bitstreams: 1 Carlos Eduardo Pires de Camargo.pdf: 6898896 bytes, checksum: a6aa82547faa73c068f21441da9ce364 (MD5) Previous issue date: 2018-10-17 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - CAPES / In the mid 1980’s several bio-inspired approaches emerged to the study of artificial intelligence. Starting from this context and from von Neumann cellular automata, the field of artificial life was developed with the objective to construct artificial systems capable to present similar behaviors to those found in biological phenomena. This thesis recovers the history of artificial life and its relationship with artificial intelligence, presents the difficulties of its development considering cartesian dualism, and demonstrates the possibility of a more adequate way of research based on the hypothesis of continuity between mind and matter, typical of the general semiotics of Charles Sanders Peirce. Through peircean semiotics and using the fundamentals of biosemiotics, the semiotic transposition technique is developed, a set of diagrammatic operations to support the study of artificial life. This technique studies the semiotic processes underlying biological phenomena. Then, through isomorphism, derived from the category theory, a finite automata can be created to computationally express certain aspects of the original biological processes. Throughout the research, the learning and memory behavior of a sea slug species, Aplysia californica, was used as an auxiliary element for the formalization of semiotic transposition. Two other biological phenomena — the genetic translation and the vacancy chain dynamics related to the Pagurus longicarpus, a species of crab — were considered as case studies to demonstrate the general character of the semiotic transposition. It is concluded that the use of semiotic theory as the basis for the study of artificial life constitutes an effective instrument to the creation of bio inspired computational devices / Em meados da década de 1980 surgem várias abordagens bioinspiradas para o estudo da inteligência artificial. Partindo-se deste contexto e dos autômatos celulares de von Neumann, foi desenvolvido o campo da vida artificial com o objetivo de construir sistemas artificiais capazes de apresentar comportamentos semelhantes aos encontrados nos fenômenos biológicos. Esta tese recupera a história da vida artificial e de sua relação com a inteligência artificial, apresenta as dificuldades de seu desenvolvimento através de posições baseadas no dualismo cartesiano, e demonstra a possibilidade de um caminho mais adequado de pesquisa tendo como hipótese a continuidade entre mente e matéria, própria da semiótica geral de Charles Sanders Peirce. Através da semiótica peirceana e de fundamentos da biossemiótica, desenvolve-se a técnica de transposição semiótica, um conjunto de operações diagramáticas para auxiliar o estudo da vida artificial. Esta técnica realiza o levantamento dos processos semióticos subjacentes aos fenômenos biológicos para que sejam criados, através de isomorfismo derivado da teoria das categorias, autômatos finitos capazes de expressar, computacionalmente, certos aspectos dos processos biológicos originais. Ao longo da pesquisa, foi utilizado o comportamento de aprendizagem e memória de um molusco marinho, a Aplysia californica, como elemento auxiliar para a formalização da transposição semiótica. Outros dois fenômenos biológicos — a tradução gênica e a dinâmica da cadeia de vacância relativa ao caranguejo Pagurus longicarpus — foram considerados para o estudo de casos que comprovam o caráter geral da transposição semiótica. Conclui-se que o uso da teoria semiótica como fundamento para o estudo da vida artificial constitui-se em instrumento efetivo para a criação de dispositivos computacionais biologicamente inspirados

Network reciprocity describes the emergence of cooperative behaviour where interactions are constrained by incomplete network connectivity. It has been widely studied as an enabling mechanism for the emergence of cooperation and may be of particular interest in explaining cooperative behaviours amongst unrelated individuals or in organisms of lower cognitive abilities. Research in this area has been galvanised by the finding that heterogeneous topology promotes cooperation. Consequently there has been a strong focus on scale-free networks; however, such networks typically presuppose formative mechanisms based on preferential attachment, a process which has no general explanation. This assumption may give rise to models of cooperation that implicitly encode capabilities only generally found in more complex forms of life, thus constraining their relevance with regards to the real world. By considering the connectivity of populations to be dynamic, rather than fixed, cooperation can exist at lower levels of heterogeneity. This thesis demonstrates that a model of network fluctuation, based on random rather than preferential growth, supports cooperative behaviour in simulated social networks of only moderate heterogeneity, thus overcoming difficulties associated with explanations based on scale-free networks. In addition to illustrating the emergence and persistence of cooperation in existing networks, we also demonstrate how cooperation may evolve in networks during their growth. In particular our model supports the emergence of cooperation in populations where it is originally absent. The combined impact of our findings increases the generality of reciprocity as an explanation for cooperation in networks.

A evolução de redes neurais artificiais encontra aplicações em diversos campos na área de aprendizado de máquina, em particular, simulações de vida artificial onde uma população de indivíduos controlados por redes neurais se adaptam num ambiente virtual a fim de realizar uma determinada tarefa. Similar ao processo natural pelo qual o comportamento do organismo se modifica filogeneticamente através da complexificação do sistema nervoso, tais simulações oferecem uma nova abordagem sintética no estudo da inteligência, em contraposição aos métodos simbólicos tradicionais. Um recente método, conhecido por NEAT (NeuroEvolution of Augmenting Topologies), é capaz de obter os pesos e a própria topologia de rede neural utilizando algoritmos genéticos. A codificação utilizada pelo NEAT é flexível o suficiente para permitir evolução aberta e arquiteturas neurais arbitrárias. Este trabalho apresenta uma implementação do NEAT que pode ser utilizada em conjunto com um simulador de propósito geral, chamado Breve, formando uma plataforma para experimentos de vida artificial. A implementação proposta também estende o NEAT para lidar com redes neurais dinâmicas, onde o nível de ativação dos neurônios varia continuamente no tempo. Este novo modelo é comparado com o método tradicional numa tarefa clássica de controle não-supervisionado, mostrando um aumento de eficiência na busca pela solução do problema. Os resultados obtidos motivam o uso desta plataforma para experimentos de vida artificial, onde uma população de indivíduos interage continuamente com um ambiente dinâmico, se adaptando ao longo das gerações. / The evolution of artificial neural networks has a wide range of applicability in diverse areas in the field of machine learning, particularly, in artificial life simulations where a population of individuals, controlled by neural networks, adapts in a virtual environment in order to solve a given task. Resembling the natural process in which an organism\'s behavior is subjected to phylogenetic modifications through the complexification of the nervous system, such simulations offer a new synthetic approach in the investigation of intelligence, counter posing traditional symbolic methods. A recent method known as NEAT (NeuroEvolution of Augmenting Topologies), is able to obtain the synaptic weights and the topology with the aid of genetic algorithms. The encoding used by NEAT is flexible enough to allow for open-ended evolution and arbitrary neural architectures. This work presents a NEAT implementation especially suitable to be used with a general purpose simulator known as Breve, constituting a framework for artificial life experiments. The proposed implementation extends NEAT to include dynamical neuron models, where their inner state continuously varies over time. The new model is then compared to the traditional method in a classic unsupervised control benchmark task, showing an efficiency increase while solving the problem. The obtained results motivate the proposed framework for general experiments in artificial life, in which a population of individuals continuously interact with a dynamical environment, adapting through generations.

No description available.

The creation of expressive styles for digital art is one of the primary goals in non-photorealistic rendering. In this paper, we introduce a swarm-based multi-agent system that is capable of producing expressive imagery through the use of multiple digital images. At birth, agents in our system are assigned a digital image that represents their 'aesthetic ideal'. As agents move throughout a digital canvas they try to 'realize' their ideal by modifying the pixels in the digital canvas to be closer to the pixels in their aesthetic ideal. When groups of agents with different aesthetic ideals occupy the same canvas, a new image is created through the convergence of their competing aesthetic goals. We use our system to explore the concepts and techniques from a number of Modern Art movements and to create an interactive media installation. The simple implementation and effective results produced by our system makes a compelling argument for more research using swarm-based multi-agent systems for non-photorealistic rendering. / Graduate

While the use of microbial model systems in experimental evolution has made great contributions to our understanding of evolutionary processes, technological limitations and the problems of transparency they cause continue to inhibit their use in understanding even the most basic evolutionary phenomena. Conventional mathematical models are too constraining in that the range of genotypes and fitnesses must be designated at the outset, and so such models cannot be used to describe truly open-ended systems. In this thesis, I use Artificial Life technology to investigate patterns and mechanisms of evolution over short and long periods of time in a simulated chemostat-type system. The system may be rendered completely transparent, and is "open" in that genotypes with unique sequences and fitness arise unpredictably through mutation and selection. / The results demonstrate that Artificial Life technology is an open-ended, yet tractable system that may be used satisfactorily to investigate problems that he beyond the reach of current theory and biotechnology. (Abstract shortened by UMI.)

No description available.

No description available.

It is widely believed that we might be able produce life out of nonliving substances if we possessed the relevant knowledge. Thus synthetic biology is said to be on the way towards artificial life. But this is nonsense: “artificial life” cannot be thought. The idea that biological organisms could be produced reflects a misunderstandig of the concept “life”. Life is formally characterized by the fact that that which in the case of artifacts is three distinct activities – being something, producing it, and using it – is one. For a living being, to be is to be the source of its own activity through its own activity. Hence, if there is an activity of producing distinct from being what is produced – as would have to be the case in artificial life – what is thus produced is not life.