KittyCat: a cognitive model of structure-form discovery

Cognition is a core subject to understand how humans think and behave. In that sense, it is clear that Cognition is a great ally to Management, as the later deals with people and is very interested in how they behave, think, and make decisions. However, even though Cognition shows great promise as a field, there are still many topics to be explored and learned in this fairly new area. Kemp & Tenembaum (2008) tried to a model graph-structure problem in which, given a dataset, the best underlying structure and form would emerge from said dataset by using bayesian probabilistic inferences. This work is very interesting because it addresses a key cognition problem: learning. According to the authors, analogous insights and discoveries, understanding the relationships of elements and how they are organized, play a very important part in cognitive development. That is, this are very basic phenomena that allow learning. Human beings minds do not function as computer that uses bayesian probabilistic inferences. People seem to think differently. Thus, we present a cognitively inspired method, KittyCat, based on FARG computer models (like Copycat and Numbo), to solve the proposed problem of discovery the underlying structural-form of a dataset.

Descobrindo modelos de previsão para a inflação brasileira : uma análise a partir do algoritmo autometrics

O presente trabalho tem como objetivo avaliar a capacidade preditiva de modelos econométricos de séries de tempo baseados em indicadores macroeconômicos na previsão da inflação brasileira (IPCA). Os modelos serão ajustados utilizando dados dentro da amostra e suas projeções ex-post serão acumuladas de um a doze meses à frente. As previsões serão comparadas a de modelos univariados como autoregressivo de primeira ordem - AR(1) - que nesse estudo será o benchmark escolhido. O período da amostra vai de janeiro de 2000 até agosto de 2015 para ajuste dos modelos e posterior avaliação. Ao todo foram avaliadas 1170 diferentes variáveis econômicas a cada período a ser projetado, procurando o melhor conjunto preditores para cada ponto no tempo. Utilizou-se o algoritmo Autometrics para a seleção de modelos. A comparação dos modelos foi feita através do Model Confidence Set desenvolvido por Hansen, Lunde e Nason (2010). Os resultados obtidos nesse ensaio apontam evidências de ganhos de desempenho dos modelos multivariados para períodos posteriores a 1 passo à frente.

Comparação de previsões para a produção industrial brasileira considerando efeitos calendário e modelos agregados e desagregados

O trabalho tem como objetivo verificar a existência e a relevância dos Efeitos Calendário em indicadores industriais. São explorados modelos univariados lineares para o indicador mensal da produção industrial brasileira e alguns de seus componentes. Inicialmente é realizada uma análise dentro da amostra valendo-se de modelos estruturais de espaço-estado e do algoritmo de seleção Autometrics, a qual aponta efeito significante da maioria das variáveis relacionadas ao calendário. Em seguida, através do procedimento de Diebold-Mariano (1995) e do Model Confidence Set, proposto por Hansen, Lunde e Nason (2011), são realizadas comparações de previsões de modelos derivados do Autometrics com um dispositivo simples de Dupla Diferença para um horizonte de até 24 meses à frente. Em geral, os modelos Autometrics que consideram as variáveis de calendário se mostram superiores nas projeções de 1 a 2 meses adiante e superam o modelo simples em todos os horizontes. Quando se agrega os componentes de categoria de uso para formar o índice industrial total, há evidências de ganhos nas projeções de prazo mais curto.

Técnicas de controlo não-linear baseadas em Redes Neuronais: do algoritmo à implementação

O presente trabalho analisa soluções de controlo não-linear baseadas em Redes Neuronais e apresenta a sua aplicação a um caso prático, desde o algoritmo de treino até à implementação física em hardware. O estudo inicial do estado da arte da utilização das Redes Neuronais para o controlo leva à proposta de soluções iterativas para a definição da arquitectura das mesmas e para o estudo das técnicas de Regularização e Paragem de Treino Antecipada, através dos Algoritmos Genéticos e à proposta de uma forma de validação dos modelos obtidos. Ao longo da tese são utilizadas quatro malhas para o controlo baseado em modelos, uma das quais uma contribuição original, e é implementado um processo de identificação on-line, tendo por base o algoritmo de treino Levenberg-Marquardt e a técnica de Paragem de Treino Antecipada que permite o controlo de um sistema, sem necessidade de recorrer ao conhecimento prévio das suas características. O trabalho é finalizado com um estudo do hardware comercial disponível para a implementação de Redes Neuronais e com o desenvolvimento de uma solução de hardware utilizando uma FPGA. De referir que o trabalho prático de teste das soluções apresentadas é realizado com dados reais provenientes de um forno eléctrico de escala reduzida.

Implementação do algoritmo (RTM) para processamento sísmico em arquiteturas não convencionais

With the growth of energy consumption worldwide, conventional reservoirs, the reservoirs called "easy exploration and production" are not meeting the global energy demand. This has led many researchers to develop projects that will address these needs, companies in the oil sector has invested in techniques that helping in locating and drilling wells. One of the techniques employed in oil exploration process is the reverse time migration (RTM), in English, Reverse Time Migration, which is a method of seismic imaging that produces excellent image of the subsurface. It is algorithm based in calculation on the wave equation. RTM is considered one of the most advanced seismic imaging techniques. The economic value of the oil reserves that require RTM to be localized is very high, this means that the development of these algorithms becomes a competitive differentiator for companies seismic processing. But, it requires great computational power, that it still somehow harms its practical success. The objective of this work is to explore the implementation of this algorithm in unconventional architectures, specifically GPUs using the CUDA by making an analysis of the difficulties in developing the same, as well as the performance of the algorithm in the sequential and parallel version

Effects of corn particle size and physical form of the diet on the gastrointestinal structures of broiler chickens

The objective of this experiment was to investigate the effects of different particle sizes, expressed as Geometric Mean Diameter (GMD) of corn (0.336mm, 0.585mm, 0.856mm and 1.12mm) of mash and pelleted broiler chicken diets on the weight of the gizzard, duodenum and jejunum+ileum; on the pH of the gizzard and small intestine and on the characteristics of the duodenal mucous layer (number and height of villi and crypt depth) in 42-day-old broilers. The physical form and the particle size of the diet had no significant effect on gizzard and intestine pH (p > 0.05). A greater gizzard weight was seen in the birds receiving pelleted diet and particle size of 0.336mm (p < 0.008). However, for the particle sizes of 0.856 and 1.12 mm, a greater weight was found in birds that received mash diet (p < 0.039 and p < 0.006, respectively). Also, gizzard weight was greater with increasing corn GMD independent of the physical form of the diet. In the mash diet, the increase in particle size promoted a quadratic response in the weight of duodenum and jejunum + ileum. The pelleted diet promoted a greater number of villi per transverse duodenum cut (p < 0.007) and greater crypt depth (p < 0.05). As the particle size increased, there was a linear increase of villus height and crypt depth in the duodenum, irrespective of the physical form of the diet.

Busca heurística através de algoritmo genético e memético com construção de vocábulos para o problema de atribuição de localidades a anéis Sonet

Telecommunications play a key role in contemporary society. However, as new technologies are put into the market, it also grows the demanding for new products and services that depend on the offered infrastructure, making the problems of planning telecommunications networks, despite the advances in technology, increasingly larger and complex. However, many of these problems can be formulated as models of combinatorial optimization, and the use of heuristic algorithms can help solving these issues in the planning phase. In this project it was developed two pure metaheuristic implementations Genetic algorithm (GA) and Memetic Algorithm (MA) plus a third hybrid implementation Memetic Algorithm with Vocabulary Building (MA+VB) for a problem in telecommunications that is known in the literature as Problem SONET Ring Assignment Problem or SRAP. The SRAP arises during the planning stage of the physical network and it consists in the selection of connections between a number of locations (customers) in order to meet a series of restrictions on the lowest possible cost. This problem is NP-hard, so efficient exact algorithms (in polynomial complexity ) are not known and may, indeed, even exist

Algoritmo evolutivo paralelo para o problema de atribuição de localidades a anéis em redes sonet/sdh

The telecommunications play a fundamental role in the contemporary society, having as one of its main roles to give people the possibility to connect them and integrate them into society in which they operate and, therewith, accelerate development through knowledge. But as new technologies are introduced on the market, increases the demand for new products and services that depend on the infrastructure offered, making the problems of planning of telecommunication networks become increasingly large and complex. Many of these problems, however, can be formulated as combinatorial optimization models, and the use of heuristic algorithms can help solve these issues in the planning phase. This paper proposes the development of a Parallel Evolutionary Algorithm to be applied to telecommunications problem known in the literature as SONET Ring Assignment Problem SRAP. This problem is the class NP-hard and arises during the physical planning of a telecommunication network and consists of determining the connections between locations (customers), satisfying a series of constrains of the lowest possible cost. Experimental results illustrate the effectiveness of the Evolutionary Algorithm parallel, over other methods, to obtain solutions that are either optimal or very close to it

Um algoritmo híbrido para o problema de roteamento de veículos com frotas heterogêneas

This paper aims to propose a hybrid meta-heuristics for the Heterogeneous Fleet Vehicle Routing Problem (HVRP), which is a combinatorial optimization problem NP-hard, and is characterized by the use of a limited fleet consists of different vehicles with different capacities. The hybrid method developed makes use of a memetic algorithm associated with the component optimizer Vocabulary Building. The resulting hybrid meta-heuristic was implemented in the programming language C + + and computational experiments generated good results in relation to meta-heuristic applied in isolation, proving the efficiency of the proposed method.

Algoritmo Q-learning como estratégia de exploração e/ou explotação para metaheurísticas GRASP e algoritmo genético

Techniques of optimization known as metaheuristics have achieved success in the resolution of many problems classified as NP-Hard. These methods use non deterministic approaches that reach very good solutions which, however, don t guarantee the determination of the global optimum. Beyond the inherent difficulties related to the complexity that characterizes the optimization problems, the metaheuristics still face the dilemma of xploration/exploitation, which consists of choosing between a greedy search and a wider exploration of the solution space. A way to guide such algorithms during the searching of better solutions is supplying them with more knowledge of the problem through the use of a intelligent agent, able to recognize promising regions and also identify when they should diversify the direction of the search. This way, this work proposes the use of Reinforcement Learning technique - Q-learning Algorithm - as exploration/exploitation strategy for the metaheuristics GRASP (Greedy Randomized Adaptive Search Procedure) and Genetic Algorithm. The GRASP metaheuristic uses Q-learning instead of the traditional greedy-random algorithm in the construction phase. This replacement has the purpose of improving the quality of the initial solutions that are used in the local search phase of the GRASP, and also provides for the metaheuristic an adaptive memory mechanism that allows the reuse of good previous decisions and also avoids the repetition of bad decisions. In the Genetic Algorithm, the Q-learning algorithm was used to generate an initial population of high fitness, and after a determined number of generations, where the rate of diversity of the population is less than a certain limit L, it also was applied to supply one of the parents to be used in the genetic crossover operator. Another significant change in the hybrid genetic algorithm is the proposal of a mutually interactive cooperation process between the genetic operators and the Q-learning algorithm. In this interactive/cooperative process, the Q-learning algorithm receives an additional update in the matrix of Q-values based on the current best solution of the Genetic Algorithm. The computational experiments presented in this thesis compares the results obtained with the implementation of traditional versions of GRASP metaheuristic and Genetic Algorithm, with those obtained using the proposed hybrid methods. Both algorithms had been applied successfully to the symmetrical Traveling Salesman Problem, which was modeled as a Markov decision process

Aprendizado por Reforço com Valores deInfluência em Sistemas Multi-Agente

We propose a new paradigm for collective learning in multi-agent systems (MAS) as a solution to the problem in which several agents acting over the same environment must learn how to perform tasks, simultaneously, based on feedbacks given by each one of the other agents. We introduce the proposed paradigm in the form of a reinforcement learning algorithm, nominating it as reinforcement learning with influence values. While learning by rewards, each agent evaluates the relation between the current state and/or action executed at this state (actual believe) together with the reward obtained after all agents that are interacting perform their actions. The reward is a result of the interference of others. The agent considers the opinions of all its colleagues in order to attempt to change the values of its states and/or actions. The idea is that the system, as a whole, must reach an equilibrium, where all agents get satisfied with the obtained results. This means that the values of the state/actions pairs match the reward obtained by each agent. This dynamical way of setting the values for states and/or actions makes this new reinforcement learning paradigm the first to include, naturally, the fact that the presence of other agents in the environment turns it a dynamical model. As a direct result, we implicitly include the internal state, the actions and the rewards obtained by all the other agents in the internal state of each agent. This makes our proposal the first complete solution to the conceptual problem that rises when applying reinforcement learning in multi-agent systems, which is caused by the difference existent between the environment and agent models. With basis on the proposed model, we create the IVQ-learning algorithm that is exhaustive tested in repetitive games with two, three and four agents and in stochastic games that need cooperation and in games that need collaboration. This algorithm shows to be a good option for obtaining solutions that guarantee convergence to the Nash optimum equilibrium in cooperative problems. Experiments performed clear shows that the proposed paradigm is theoretical and experimentally superior to the traditional approaches. Yet, with the creation of this new paradigm the set of reinforcement learning applications in MAS grows up. That is, besides the possibility of applying the algorithm in traditional learning problems in MAS, as for example coordination of tasks in multi-robot systems, it is possible to apply reinforcement learning in problems that are essentially collaborative