Dans la première partie nous étudions l'apprentissage et le rappel dans des réseaux de neurones à une couche (modèle de Hopfield). Nous proposons un algorithme d'apprentissage qui est capable d'optimiser la 'stabilité', un paramètre qui décrit la qualité de la représentation d'un pattern dans le réseau. Pour des patterns aléatoires, cet algorithme permet d'atteindre la borne théorique de Gardner. Nous étudions ensuite l'importance dynamique de la stabilité et d'un paramètre concernant la symétrie de la matrice de couplages. Puis, nous traitons le cas où les couplages ne peuvent prendre que deux valeurs (inhibiteur, excitateur). Pour ce modèle nous établissons les limites supérieures de la capacité par un calcul numérique, et nous proposons une solution analytique. La deuxième partie de la thèse est consacrée à une étude détaillée - du point de vue de la physique statistique - du problème du voyageur de commerce. Nous étudions le cas spécial d'une matrice aléatoire de connexions. Nous exposons la théorie de ce problème (suivant la méthode des répliques) et la comparons aux résultats d'une étude numérique approfondie.

Thesis (Ph. D.)--University of Texas at Austin, 2000. / Vita. Includes bibliographical references (leaves 56-62). Available also in a digital version from Dissertation Abstracts.

The field of statistical research in weather allows for the application of old and new methods, some of which may describe relationships between certain variables better such as temperatures and pressure. The objective of this study was to apply a variety of traditional and novel statistical methods to analyze data from the National Data Buoy Center, which records among other variables barometric pressure, atmospheric temperature, water temperature and dew point temperature. The analysis included attempts to better describe and model the data as well as to make estimations for certain variables. The following statistical methods were utilized: linear regression, non-response analysis, residual analysis, descriptive statistics, parametric analysis, Kolmogorov-Smirnov test, autocorrelation, normal approximation for the binomial, and chi-squared test of independence. Of the more significant results, one was establishing the Johnson SB as the best fitting parametric distribution for a group of pressures and another was finding that there was high autocorrelation in atmospheric temperature and pressure for small lags. This topic remains conducive to future research, and such endeavors may strengthen the field of applied statistics and improve our understanding of various weather entities.

Creating an accurate hurricane location forecasting model is of the utmost importance because of the safety measures that need to occur in the days and hours leading up to a storm's landfall. Hurricanes can be incredibly deadly and costly, but if people are given adequate warning, many lives can be spared. This thesis seeks to develop an accurate model for predicting storm location based on previous location, previous wind speed, and previous pressure. The models are developed using hurricane data from 1980-2009.

Many of the open problems of current interest in probability and statistics involve complicated data sets that do not satisfy the strong assumptions of being independent and identically distributed. Often, the samples are known only empirically, and making assumptions about underlying parametric distributions is not warranted by the insufficient information available. Under such circumstances, the usual Fisher or parametric Bayes approaches cannot be used to model the data or make predictions. However, this situation is quite often encountered in some of the main challenges facing statistical, data-driven studies of climate change, clinical studies, or financial markets, to name a few. We propose a novel approach, based on large deviations theory, convex optimization, and recent results on surrogate loss functions for classifier-type problems, that can be used in order to estimate the probability of large deviations for complicated data. This may include, for instance, highdimensional data, highly-correlated data, or very sparse data. The thesis introduces the new approach, reviews the current known theoretical results, and then presents a number of numerical explorations meant to quantify how far the approximation of survival functions via large deviations principle can be taken, once we leave the limitations imposed by the existing theoretical results. The explorations are encouraging, indicating that indeed the new approximation scheme may be very efficient and can be used under much more general conditions than those warranted by the current theoretical thresholds. After applying the new methodology to two important contemporary problems (atmospheric CO2 data and El Ni~no/La Ni~na phenomena), we conclude with a summary outline of possible further research.

This is the first paper to measure the efficiency of the Japan Professional Football League clubs both the first and the second divisions. In Chapter 1, a non-parametric method Data Envelopment Development (DEA) is used and the data covers six seasons from 2005 to 2010. The input variables are payroll, cost besides payroll, and total assets. The output variables are attendance, revenue, and points awarded. I use different output combinations in order to check the sensitivity of the efficiency of the clubs after the original composition. This is also the first research to include more than one division of the Professional Football League and hence, the promotion and relegation impact on the efficiency can be analyzed using unique data such as Tokyo Verdy 1969. Tokyo Verdy 1969 operated inefficiently in the second division because it spent so much on inputs hoping for promotion. It was efficient when in the first division. The results indicate that athletic rank in the league is not correlated with the efficiency scores. The efficient clubs in the second division are all ranked at the bottom in the league and this is because they have limited resource inputs, no expectation to promote, and because the expansion policy of the league precludes relegation. Chapter 2 is an extension of Chapter 1. In this chapter I check the exogenous factors impacting the efficiency scores but not involved in the DEA analysis as the input variables. I aim to estimate the relationship between the input-oriented DEA efficiency scores under the constant returns to scale assumption and use an exogenous variable ordinary least square (OLS) model to check the relationship between the efficiency scores and exogenous variables. I regress the DEA efficiency scores on all of the exogenous variables collected from various resources during the sample period. Chapter 3 estimates the productivity and efficiencies of the football clubs in Japan Professional Football League. This chapter is an extension of the first chapter. In this chapter I check the dynamic change of Total Factor Productivity (TFP) based on the calculation of the Malmquist Index, which consists of efficiency change and technical change between two time periods. Additionally, the production frontier used in this chapter was built by the non-parametric input-oriented CRS DEA approach as applied in the first chapter. Based on the results of the Malmquist Index, we find if the change in the TFP growth as increasing, declining or remaining the same.

Significant phylogenetic codivergence between plant or animal hosts (H) and their symbionts or parasites (P) indicate the importance of their interactions on evolutionary time scales. However, valid and realistic methods to test for codivergence are not fully developed. One of the systems where possible codivergence has been of interest involves the large subfamily of temperate grasses (Pooideae) and their endophytic fungi (epichloae). Here we introduce the MRCALink (most-recent-common-ancestor link) method and use it to investigate the possibility of grass-epichloё codivergence. MRCALink applied to ultrametric H and P trees identifies all corresponding nodes for pairwise comparisons of MRCA ages. The result is compared to the space of random H and Ptree pairs estimated by a Monte Carlo method. Compared to tree reconciliation the method is less dependent on tree topologies (which often can be misleading), and it crucially improves on phylogeny-independent methods such as ParaFit or the Mantel test by eliminating an extreme (but previously unrecognized) distortion of node-pair sampling. Analysis of 26 grass species-epichloё species symbioses did not reject random association of H and P MRCA ages. However, when five obvious host jumps were removed the analysis significantly rejected random association and supported grass-endophyte codivergence. Interestingly, early cladogenesis events in the Pooideae corresponded to early cladogenesis events in epichloae, suggesting concomitant origins of this grass subfamily and its remarkable group of symbionts.

Thesis (Ph. D.)--University of Missouri-Columbia, 1997. / Typescript. Vita. Includes bibliographical references (leaves 106-112). Also available on the Internet.

Thesis (Ph. D.)--University of Missouri-Columbia, 1997. / Typescript. Vita. Includes bibliographical references (leaves 106-112). Also available on the Internet.

Thesis (Ph. D. in Education and Human Development)--Vanderbilt University, Aug. 2004. / Title from title screen. Includes bibliographical references.