No description available.

O aprendizado de máquina consiste em conceitos e técnicas que permitem aos computadores melhorar seu desempenho com a experiência, ou em outras palavras, aprender com dados. Duas de suas principais categorias são o aprendizado não-supervisionado e o semissupervisionado, que respectivamente consistem em inferir padrões em bases cujos dados não têm rótulo (classe) e classificar dados em bases parcialmente rotuladas. Embora muito estudado, trata-se de um campo repleto de desafios e com muitos tópicos abertos. Sistemas dinâmicos coletivos, por sua vez, são sistemas constituídos por muitos indivíduos, cada qual um sistema dinâmico por si só, de modo que todos eles agem coletivamente, ou seja, a ação de cada indivíduo é influenciada pela ação dos vizinhos. Uma característica notável desses sistemas é que padrões globais podem surgir espontaneamente das interações locais entre os indivíduos, fenômeno conhecido como emergência. Os desafios intrínsecos e a relevância do tema vêm motivando sua pesquisa em diversos ramos da ciência e da engenharia. Este trabalho de doutorado consiste no desenvolvimento e análise de modelos dinâmicos coletivos para o aprendizado de máquina, especificamente suas categorias não-supervisionada e semissupervisionada. As tarefas de segmentação de imagens e de detecção de comunidades em redes, que de certo modo podem ser entendidas como tarefas do aprendizado de máquina, são também abordadas. Em especial, desenvolvem-se modelos nos quais a movimentação dos objetos é determinada pela localização e velocidade de seus vizinhos. O sistema dinâmico assim modelado é então conduzido a um estado cujo padrão formado por seus indivíduos realça padrões subjacentes do conjunto de dados. Devido ao seu caráter auto-organizável, os modelos aqui desenvolvidos são robustos e as informações geradas durante o processo (valores das variáveis do sistema) são ricas e podem, por exemplo, revelar características para realizar soft labeling e determinar classes sobrepostas. / Machine learning consists of concepts and techniques that enable computers to improve their performance with experience, i.e., learn from data. Unsupervised and semi-supervised learning are important categories of machine learning, which respectively consists of inferring patterns in datasets whose data have no label (class) and classifying data in partially-labeled datasets. Although intensively studied, machine learning is still a field full of challenges and with many open topics. Collective dynamical systems, in turn, are systems made of a large group of individuals, each one a dynamical system by itself, such that all of them behave collectively, i.e., the action of each individual is influenced by the action of its neighbors. A remarkable feature of those systems is that global patterns may spontaneously emerge from the local interactions among individuals, a phenomenon known as emergence. Their relevance and intrinsic challenges motivate research in various branches of science and engineering. In this doctorate research, we develop and analyze collective dynamical models for their usage in machine-learning tasks, specifically unsupervised and semi-supervised ones. Image segmentation and network community detection are also addressed, as they are related to machine learning as well. In particular, we propose to work on models in which the objects motion is determined by the location and velocity of their neighbors. By doing so, the dynamical system reaches a configuration in which the patterns developed by the set of individuals highlight underlying patterns of the dataset. Due to their self-organizing nature, it is also expected that the models can be robust and the information generated during the process (values of the system variables) can be rich and reveal, for example, features to perform soft labeling and determine overlapping classes.

L'activité neuronale est souvent considérée en neuroscience cognitive par la réponse évoquée mais l'essentiel de l'énergie consommée par le cerveau permet d'entretenir les dynamiques spontanées des réseaux corticaux. L'utilisation combinée d'algorithmes de classification (K means, arbre hirarchique, SOM) sur des enregistrements intracellulaires du cortex visuel primaire du chat nous permet de définir des classes de dynamiques neuronales et de les comparer l'activité évoquée par un stimulus visuel. Ces dynamiques peuvent être étudiées sur des systèmes simplifiés (FitzHugh-Nagumo, systèmes dynamiques hybrides, Wilson-Cowan) dont nous présentons l'analyse. Enfin, par des simulations de réseaux composés de colonnes de neurones, un modèle du cortex visuel primaire nous permet d'étudier les dynamiques spontanées et leur effet sur la réponse à un stimulus. Après une période d'apprentissage pendant laquelle des stimuli visuels sont presentés, des vagues de dépolarisation se propagent dans le réseau. L'étude des correlations dans ce réseau montre que les dynamiques spontanées reflètent les propriétés fonctionnelles acquises au cours de l'apprentissage.

Distributed learning is the iterative process of decision-making in the presence of other decision-makers. In recent years, researchers across fields as disparate as engineering, biology, and economics have identified mathematically congruous problem formulations at the intersection of their disciplines. In particular, stochastic processes, game theory, and control theory have been brought to bare on certain very basic and universal questions. What sort of environments are conducive to distributed learning? Are there any generic algorithms offering non-trivial performance guarantees for a large class of models? The first half of this thesis makes contributions to two particular problems in distributed learning, self-assembly and language. Self-assembly refers to the emergence of high-level structures via the aggregate behavior of simpler building blocks. A number of algorithms have been suggested that are capable of generic self-assembly of graphs. That is, given a description of the objective they produce a policy with a corresponding performance guarantee. These guarantees have been in the form of deterministic convergence results. We introduce the notion of stochastic stability to the self-assembly problem. The stochastically stable states are the configurations the system spends almost all of its time in as a noise parameter is taken to zero. We show that in this framework simple procedures exist that are capable of self-assembly of any tree under stringent locality constraints. Our procedure gives an asymptotically maximum yield of target assemblies while obeying communication and reversibility constraints. We also present a slightly more sophisticated algorithm that guarantees maximum yields for any problem size. The latter algorithm utilizes a somewhat more presumptive notion of agents' internal states. While it is unknown whether an algorithm providing maximum yields subject to our constraints can depend only on the more parsimonious form of internal state, we are able to show that such an algorithm would not be able to possess a unique completing rule--- a useful feature for analysis. We then turn our attention to the problem of distributed learning of communication protocols, or, language. Recent results for signaling game models establish the non-negligible possibility of convergence, under distributed learning, to states of unbounded efficiency loss. We provide a tight lower bound on efficiency and discuss its implications. Moreover, motivated by the empirical phenomenon of linguistic drift, we study the signaling game under stochastic evolutionary dynamics. We again make use of stochastic stability analysis and show that the long-run distribution of states has support limited to the efficient communication systems. We find that this behavior is insensitive to the particular choice of evolutionary dynamic, a fact that is intuitively captured by the game's potential function corresponding to average fitness. Consequently, the model supports conclusions similar to those found in the literature on language competition. That is, we expect monomorphic language states to eventually predominate. Homophily has been identified as a feature that potentially stabilizes diverse linguistic communities. We find that incorporating homophily in our stochastic model gives mixed results. While the monomorphic prediction holds in the small noise limit, diversity can persist at higher noise levels or as a metastable phenomenon. The contributions of the second half of this thesis relate to more basic issues in distributed learning. In particular, we provide new results on the problem of distributed convergence to Nash equilibrium in finite games. A recently proposed class of games known as stable games have the attractive property of admitting global convergence to equilibria under many learning dynamics. We show that stable games can be formulated as passive input-output systems. This observation enables us to identify passivity of a learning dynamic as a sufficient condition for global convergence in stable games. Notably, dynamics satisfying our condition need not exhibit positive correlation between the payoffs and their directions of motion. We show that our condition is satisfied by the dynamics known to exhibit global convergence in stable games. We give a decision-theoretic interpretation for passive learning dynamics that mirrors the interpretation of stable games as strategic environments exhibiting self-defeating externalities. Moreover, we exploit the flexibility of the passivity condition to study the impact of applying various forecasting heuristics to the payoffs used in the learning process. Finally, we show how passivity can be used to identify strategic tendencies of the players that allow for convergence in the presence of information lags of arbitrary duration in some games.

In the 1980s and 1990s, many scientifically cognizant young novelists turned away from the physics-based tropes of entropy and chaos and chose biological concepts of order, complexity, and self-organization as their dominant metaphors. This dissertation focuses on three novels published between 1991 and 1996 that replace the notion of the encyclopedia as a closed system and model new narrative ecologies grounded in the tenets of the emergent science of complex systems. Thus, Richard Powers's The Gold-Bug Variations (1991) explores the marriage of bottom-up self-organizing systems and top-down natural selection through a narrative lens and cautions us against any worldview which does not grasp life as a complex system; Bob Shacochis's Swimming in the Volcano (1993) illustrates how richly complex global behavior emerges from the local interaction of a large number of independent agents; and, David Foster Wallace's Infinite Jest (1996) enacts a collaborative narrative of distributed causality to investigate reciprocal relationships between the individual and the multiple systems in which he is embedded. Unlike many other contemporary authors, the new encyclopedists do not shun the abundance of information in postmodern culture. Instead, as I demonstrate here, the intricate webs of their complex ecologies emerge as narrative circulates through diverse informational networks. Ecologies of Knowledge argues that these texts inaugurate a new naturalism, demanding a reconciliation between humans and the natural world and advocating an increased understanding of life's interdependent patterns and particularities. Grounded in such an awareness of ecological complexity, these large and demanding books are our survival guides for the twenty-first century. / Department of English

Orientador: Ricardo Ribeiro Gudwin / Dissertação (mestrado) - Universidade Estadual de Campinas. Faculdade de Engenharia Eletrica e de Computação / Made available in DSpace on 2018-08-08T12:38:59Z (GMT). No. of bitstreams: 1 Weingaertner_Daniel_M.pdf: 1557993 bytes, checksum: 443eb132ca2377b1579d9dabfb29655c (MD5) Previous issue date: 2003 / Resumo: Neste trabalho desenvolvemos uma análise das redes neuroenergéticas (propostas por Leonid B. Emelyanov-Yaroslavsky) e a especificação de um agente inteligente constru'ido com estas redes, comparando-o com outras especificaçoes de agentes existentes na literatura e também avaliando suas capacidades semióticas. As redes neuroenergéticas caracterizam-se por serem autoorganizáveis em torno do objetivo de minimização do consumo de energia de seus neurônios. A partir deste objetivo, e dadas algumas restrições, Emelyanov-Yaroslavsky sugere que deveriam surgir no agente neuroenergético características típicas de sistemas inteligentes como memória, volição, aprendizado, capacidade de generalização, etc. Este trabalho visa dar os primeiros passos na validação das propostas de Emelyanov-Yaroslavsky por meio da compreensão das características básicas do modelo e sua reprodução e simulação. Uma versão computacional da rede neuroenergética foi implementada demonstrando sua viabilidade operacional e capacidade de auto-organização. Embora não tenha sido implementado, o modelo do agente neuroenergético abre perspectivas no sentido de criar sistemas cognitivos capazes de atuar nos mais diversos ambientes e domínios / Abstract: This work presents an analysis of the neuroenergetic networks (proposed by Leonid B. Emelyanov-Yaroslavsky) and the specification of an intelligent agent constructed with these networks, comparing it to other existing agent specifications in the literature and also evaluating its semiotic capabilities. The neuroenergetic networks are characterized by their capability of selforganizing, aiming at minimizing the energy consumption of their neurons. With this aim in mind, and given some restrictions, Emelyanov-Yaroslavsky suggests that the neuroenergetic agent should develop some typical characteristics of intelligent systems such as: memory, volition, learning and, generalizationcapabilities, etc. This work aims at making the first steps validating Emelyanov-Yaroslavsky¿s proposals through the comprehension of the model¿s basic features and its reproduction and simulation. A computational version of the neuroenergetic network was implemented, demonstrating its operational viability and capacity of selforganization. Even though it has not yet been implemented, the model of the neuroenergetic agent opens perspectives in the direction of creating cognitive systems, capable to act in most diverse environments and domains / Mestrado / Engenharia de Computação / Mestre em Engenharia Elétrica

Network Direct Selling Organisations (NDSOs) exist in more than 50 countries and have more than 74 million members. The most recent statistical information reveals that the vast majority of members do not earn significant income. Criticism of these organisations revolves around the ethicality of consumption, the commercialisation of personal relationships, and the exploitation of unrealistic expectations. This study aims to explore how communication creates networks that sustain an industry of this kind despite the improbability of its existence. The study commences with a description of NDSOs from historical, operational, tactical, and strategic perspectives. Given the broader context created by the global presence of this industry, cybernetics has been selected as a meta-theoretical perspective for the study of communication. The more recent development of second-order cybernetics and social autopoiesis are introduced to communication theory as a field. Niklas Luhmann‟s new social theory of communication is assessed and applied in relation to existing communication theory. New conceptual models are developed to explore communication as the unity of the synthesis of information, utterance, understanding, and expectations as selections that occur both consciously and unconsciously, intentionally and unintentionally. These models indicate the multiplexity of individual and social operationally closed, yet informationally open systems, and they are used here to provide a systemic and coherent alternative to orthodox communication approaches to the study of organisations. The study adopts a constructivist epistemological stance and propounds throughout the necessity of further interdisciplinary collaboration. The study concludes that individuals are composite unities of self-creating systems, and they co-create social systems by self-creating and co-creating meaning. Meaning is described as the continuous virtualisation and actualisation of potentialities that in turn coordinate individual and social systems‟ actions. A communication process flow model is created to provide a theoretical explanation for the existence of NDSOs as self-creating systems. The study aims to show that communication has arguably become the most pervasive discipline as a result of the globally interactive era. It is shown that second-order cybernetics and social autopoiesis raise several further questions to be explored within communication theory as a field. / Communication, first-order cybernetics, second-order cybernetics, Complexity and complex systems, autopoiesis, self-reference, recursivity, operational closure, system boundaries, Network Direct Selling Organisations / Communication / D. Litt. et Phil. (Communication)

Self-healing systems promise operating cost reductions in large-scale computing environments through the automated detection of, and recovery from, faults. However, at present there appears to be little known empirical evidence comparing the different approaches, or demonstrations that such implementations reduce costs. This thesis compares previous and current self-healing approaches before demonstrating a new, unsupervised approach that combines artificial neural networks with performance tests to perform fault identification in an automated fashion, i.e. the correct and accurate determination of which computer features are associated with a given performance test failure. Several key contributions are made in the course of this research including an analysis of the different types of self-healing approaches based on their contextual use, a baseline for future comparisons between self-healing frameworks that use artificial neural networks, and a successful, automated fault identification in cloud infrastructure, and more specifically virtual machines. This approach uses three established machine learning techniques: Naïve Bayes, Baum-Welch, and Contrastive Divergence Learning. The latter demonstrates minimisation of human-interaction beyond previous implementations by producing a list in decreasing order of likelihood of potential root causes (i.e. fault hypotheses) which brings the state of the art one step closer toward fully self-healing systems. This thesis also examines the impact of that different types of faults have on their respective identification. This helps to understand the validity of the data being presented, and how the field is progressing, whilst examining the differences in impact to identification between emulated thread crashes and errant user changes – a contribution believed to be unique to this research. Lastly, future research avenues and conclusions in automated fault identification are described along with lessons learned throughout this endeavor. This includes the progression of artificial neural networks, how learning algorithms are being developed and understood, and possibilities for automatically generating feature locality data.

O aprendizado de máquina consiste de conceitos e técnicas que permitem aos computadores melhorar seu desempenho com a experiência, ou, em outras palavras, aprender com dados. Um dos principais tópicos do aprendizado de máquina é o agrupamento de dados que, como o nome sugere, procura agrupar os dados de acordo com sua similaridade. Apesar de sua definição relativamente simples, o agrupamento é uma tarefa computacionalmente complexa, tornando proibitivo o emprego de algoritmos exaustivos, na busca pela solução ótima do problema. A importância do agrupamento de dados, aliada aos seus desafios, faz desse campo um ambiente de intensa pesquisa. Também a classe de fenômenos naturais conhecida como comportamento coletivo tem despertado muito interesse. Isso decorre da observação de um estado organizado e global que surge espontaneamente das interações locais presentes em grandes grupos de indivíduos, caracterizando, pois, o que se chama auto-organização ou emergência, para ser mais preciso. Os desafios intrínsecos e a relevância do tema vêm motivando sua pesquisa em diversos ramos da ciência e da engenharia. Ao mesmo tempo, técnicas baseadas em comportamento coletivo vêm sendo empregadas em tarefas de aprendizado de máquina, mostrando-se promissoras e ganhando bastante atenção. No presente trabalho, objetivou-se o desenvolvimento de técnicas de agrupamento baseadas em comportamento coletivo. Faz-se cada item do conjunto de dados corresponder a um indivíduo, definem-se as leis de interação local, e então os indivíduos são colocados a interagir entre si, de modo que os padrões que surgem reflitam os padrões originalmente presentes no conjunto de dados. Abordagens baseadas em dinâmica de troca de energia foram propostas. Os dados permanecem fixos em seu espaço de atributos, mas carregam certa informação a energia , a qual é progressivamente trocada entre eles. Os grupos são estabelecidos entre dados que tomam estados de energia semelhantes. Este trabalho abordou também o aprendizado semissupervisionado, cuja tarefa é rotular dados em bases parcialmente rotuladas. Nesse caso, foi adotada uma abordagem baseada na movimentação dos próprios dados pelo espaço de atributos. Procurou-se, durante todo este trabalho, não apenas propor novas técnicas de aprendizado, mas principalmente, por meio de muitas simulações e ilustrações, mostrar como elas se comportam em diferentes cenários, num esforço em mostrar onde reside a vantagem de se utilizar a dinâmica coletiva na concepção dessas técnicas / Machine learning consists of concepts and techniques that enable computers to improve their performance with experience, i.e., enable computers to learn from data. Data clustering (or just clustering) is one of its main topics, which aims to group data according to their similarities. Regardless of its simple definition, clustering is a complex computational task. Its relevance and challenges make this field an environment of intense research. The class of natural phenomena known as collective behavior has also attracted much interest. This is due to the observation that global patterns may spontaneously arise from local interactions among large groups of individuals, what is know as self-organization (or emergence). The challenges and relevance of the subject are encouraging its research in many branches of science and engineering. At the same time, techniques based on collective behavior are being employed in machine learning tasks, showing to be promising. The objective of the present work was to develop clustering techniques based on collective behavior. Each dataset item corresponds to an individual. Once the local interactions are defined, the individuals begin to interact with each other. It is expected that the patterns arising from these interactions match the patterns originally present in the dataset. Approaches based on dynamics of energy exchange have been proposed. The data are kept fixed in their feature space, but they carry some sort of information (the energy), which is progressively exchanged among them. The groups are established among data that take similar energy states. This work has also addressed the semi-supervised learning task, which aims to label data in partially labeled datasets. In this case, it has been proposed an approach based on the motion of the data themselves around the feature space. More than just providing new machine learning techniques, this research has tried to show how the techniques behave in different scenarios, in an effort to show where lies the advantage of using collective dynamics in the design of such techniques

La motivation de cette thèse de Doctorat est de modéliser quelques problèmes biologiques avec des systèmes et des équations de réaction-diffusion. La thèse est divisée en sept chapitres: 1. On modélise des ions de calcium et des protéines dans une épine dendritique mobile (une microstructure dans les neurones). On propose deux modèles, un avec des protéines qui diffusent et un autre avec des protéines fixées au cytoplasme. On démontre que le premier problème est bien posé, que le deuxième problème est presque bien posé et qu'il y a un lien continu entre les deux modèles. 2. On applique les techniques du Chapitre 1 pour un modèle d'infection virale et réponse immunitaire dans des cellules cultivées. On propose comme avant deux modèles, un avec des cellules qui diffusent et un autre avec des cellules fixées. On démontre que les deux problèmes sont bien posés et qu'il y a un lien continu entre les deux modèles. On Žtudie aussi le comportement asymptotique et la stabilité des solutions pour des temps larges, et on fait des simulations dans Matlab. 3. Dans le Chapitre 3 on montre que la croissance a deux effets positives dans la formation de motifs ou patterns. Le premier est un effet anti-explosion (anti-blow-up) car les solutions sur un domaine croissant explosent plus tard que celles sur un domaine fixé, et si la croissance est suffisamment rapide alors elle peut même empêcher l'explosion. Le deuxième est un effet stabilisant car les valeur propres sur un domaine croissant ont des parties réelles plus petites que celles sur un domaine fixé. 4. On étend la définition de front progressif à des variétés et on en étudie quelques propriétés. 5. On étudie des front progressifs sur la droite réelle. On démontre qu'il y a deux fronts progressifs qui se déplacent dans des directions opposées et qu'ils se bloquent mutuellement, générant ainsi une solution stationnaire non-triviale. Cet exemple montre que pour des modèles à diffusion non-homogène les fronts progressifs ne sont pas nécessairement des invasions. 6. On étudie des fronts progressifs sur la sphère. On démontre que pour des sous-domaines de la sphère avec des conditions aux limites de Dirichlet le front progressif est toujours bloqué, tandis que pour la sphère complète le front peut ou bien invahir ou bien être bloqué, tout en fonction des conditions initiales. 7. On étudie un problème elliptique aux valeurs propres nonlinéaires. Sur la sphère de dimension 1 on démontre l'existence de multiples solutions non-triviales avec des techniques de bifurcation. Sur la sphère de dimension n on utilise les mêmes arguments pour dŽmontrer l'existence de multiples solutions non-triviales à symétrie axiale, i.e. qui ne dépendent que de l'angle vertical.