This thesis was constructed on the foundation of two broad theoretical criticisms levelled against Bandura’s (1986) social cognitive theory. The first was the lack of clarity about what constituted the building blocks of the theory and the second was the lack of clarity about how these constituent components interacted in consistent and predictable ways as an integrated model of human behaviour. These ‘theory-level’ criticisms, which detracted from the empirical testability of social cognitive theory, seemed to have filtered down to the level of its individual building blocks. Therefore, moral disengagement, which constituted the focal variable of interest in this investigation, was not unaffected by them. Bandura’s (1986) theoretical presentation of moral disengagement as either an eight or four-dimensional construct and the empirical treatments of moral disengagement by Bandura and his colleagues as a uni-dimensional (Bandura, Barbaranelli, Caprara & Pastorelli, 1996a; Bandura, Caprara, Barbaranelli, Pastorelli & Regalia, 2001b) and a four-dimensional variable (McAlister, Bandura & Owen, 2006), raised questions about its dimensionality. The first objective of this study was to examine moral disengagement’s dimensionality and the stability of its internal factor structure (i.e. longitudinal measurement invariance) over time. The general lack of clarity about how the constituent components of social cognitive theory were expected to cohere as an integrated framework of human behaviour had specific implications for the moral disengagement construct and its temporal position relative to other social cognitive variables. The second objective of this study was to examine moral disengagement’s temporal sequences relative to select social cognitive constructs (viz. proficiency-based self-efficacy, intention, and past and future behaviour) in order to comment on the likely temporal positions of these constructs relative to each other in the context of a model for predicting antisocial behaviour. Due to the exclusive activation of moral disengagement in antisocial contexts, the examination of its dimensionality and temporal sequences was contingent on an antisocial context. Software piracy, as a specific instance of antisocial behaviour, served as the context in which moral disengagement was researched in this study. A pilot investigation was conducted to test the psychometric properties of the scales that were developed to measure moral disengagement, proficiency-based self-efficacy, intention and behaviour in this study. Once their psychometric robustness was established, these scales were used in the context of a main longitudinal investigation separated by a three to four month time-lag in order to achieve the two main research objectives. Using the structural equation modelling family of data analysis techniques (specifically, confirmatory factor analysis and path analysis), the results of the main longitudinal study revealed that moral disengagement emerged as most meaningful as a uni-dimensional construct which consisted of four aggregated sets of items which represented the clusters of moral disengagement mechanisms that were likely to be activated at the four points in the self-regulation process envisaged by Bandura (1986). The findings suggested that this factor structure was longitudinally invariant when moral disengagement was measured across two assessment waves. Moral disengagement appeared to temporally precede intention and future behaviour and to temporally follow past behaviour. Self-efficacy, however, seemed to temporally precede future behaviour and to temporally follow past behaviour but unlike moral disengagement, self-efficacy appeared to temporally follow intention. Therefore, intention appeared to completely mediate the interaction between moral disengagement and proficiency-based self-efficacy in this study. The theoretical and practical implications of these findings were examined and directions for future research were proposed.

Dois problemas de planejamento de trajetórias são tratados nesta dissertação, sendo um discreto e outro contínuo. O problema discreto consiste em estabelecer todos os estados intermediários de uma trajetória para levar um conjunto de quatro blocos de uma posição inicial à uma posição meta. O problema contínuo consiste em planejar e controlar a trajetória do braço mecânico PUMA 560. A classe de modelos que se utilizou nesta dissertação foram os modelos parcialmente recorrentes. O problema discreto foi utilizado com a finalidade de comparar os seis modelos propostos, buscando obter um modelo com bom desempenho para resolução de problemas de produção de seqüências temporais. Para o problema contínuo aplicou-se apenas o modelo que apresentou melhor desempenho na resolução do problema discreto. Em ambos os casos são apresentados como entrada para a rede, o ponto inicial e o ponto meta. Dois tipos de testes foram aplicados as arquiteturas: teste de produção e de generalização de seqüências temporais. Para cada problema foram criados quatro tipos distintos de trajetórias, com graus de complexidades diferentes. Para o problema discreto, em média, a arquitetura com realimentação da camada de saída para a camada de entrada e da camada de entrada para ela mesma, todos-para-todos, foi a que apresentou menor número de épocas e também os menores valores de erro durante o treinamento. Foi o único que conseguiu recuperar todos os padrões treinados e de forma geral apresentou melhor capacidade de generalização. Por isto, este modelo foi escolhido para ser aplicado na resolução do problema contínuo, tendo bom desempenho, conseguindo reproduzir as trajetórias treinadas com grande precisão. Para o problema discreto todos os modelos apresentaram baixa capacidade de generalização. Para o problema contínuo o modelo abordado apresentou-se de forma satisfatória mediante o acréscimo de ruído. / Two trajectory planning problems are discussed in this work, one of them being discrete and the other continuous. The discrete problem consists in establishing all the intermediate states o f a trajectory to move a set of four blocks from a initial to a goal position. The continuous problem consists in planning and controlling the trajectory of the PUMA 560 mechanical arm. The class of models utilized in this work were the partially recurrent models. The discrete problem was used in order to compare the six proposed models, aiming at the acquisition of a model with a good performance for the resolution of production of temporal sequence problems. For the continuous problem, only the model that presented better performance in solving the discrete problem was applied. The initial and goal point are presented as input for the network in both problems. Two types of tests were applied to the architectures: production and generalization of temporal sequence tests. Four distinct types of trajectories with different complexity levels were created for each problem. In average, for the discrete problem, the architecture with feedback from the output to the input layer and from input layer to itself all-to-all presented the lowest epoch number in addition to the lowest error values during the training. This was the only model that managed to recover all the patterns trained and in general presented better generalization capacity. For this reason, this model was chosen to be applied in the resolution of the continuous problem. It presented a good performance to the production of mechanical arm trajectories, managing to reproduce the trained trajectories with great accuracy. For the discrete problem, all the models presented low generalization capacity. For the continuous problem, the approached model presented itself in a satisfactmy manner by means of noise addition.

A hierarchical symbiotic framework for policy search with genetic programming (GP) is evaluated in two control-style temporal sequence learning domains. The symbiotic formulation assumes each policy takes the form of a cooperative team between multiple symbiont programs. An initial cycle of evolution establishes a diverse range of host behaviours with limited capability. The second cycle uses these initial policies as meta actions for reuse by symbiont programs. The relationship between development and ecology is explored by explicitly altering the interaction between learning agent and environment at fixed points throughout evolution. In both task domains, this developmental diversity significantly improves performance. Specifically, ecologies designed to promote good specialists in the first developmental phase and then good generalists result in much stronger organisms from the perspective of generalization ability and efficiency. Conversely, when there is no diversity in the interaction between task environment and policy learner, the resulting hierarchy is not as robust or general. The relative contribution from each cycle of evolution in the resulting hierarchical policies is measured from the perspective of multi-level selection. These multi-level policies are shown to be significantly better than the sum of contributing meta actions.

Dois problemas de planejamento de trajetórias são tratados nesta dissertação, sendo um discreto e outro contínuo. O problema discreto consiste em estabelecer todos os estados intermediários de uma trajetória para levar um conjunto de quatro blocos de uma posição inicial à uma posição meta. O problema contínuo consiste em planejar e controlar a trajetória do braço mecânico PUMA 560. A classe de modelos que se utilizou nesta dissertação foram os modelos parcialmente recorrentes. O problema discreto foi utilizado com a finalidade de comparar os seis modelos propostos, buscando obter um modelo com bom desempenho para resolução de problemas de produção de seqüências temporais. Para o problema contínuo aplicou-se apenas o modelo que apresentou melhor desempenho na resolução do problema discreto. Em ambos os casos são apresentados como entrada para a rede, o ponto inicial e o ponto meta. Dois tipos de testes foram aplicados as arquiteturas: teste de produção e de generalização de seqüências temporais. Para cada problema foram criados quatro tipos distintos de trajetórias, com graus de complexidades diferentes. Para o problema discreto, em média, a arquitetura com realimentação da camada de saída para a camada de entrada e da camada de entrada para ela mesma, todos-para-todos, foi a que apresentou menor número de épocas e também os menores valores de erro durante o treinamento. Foi o único que conseguiu recuperar todos os padrões treinados e de forma geral apresentou melhor capacidade de generalização. Por isto, este modelo foi escolhido para ser aplicado na resolução do problema contínuo, tendo bom desempenho, conseguindo reproduzir as trajetórias treinadas com grande precisão. Para o problema discreto todos os modelos apresentaram baixa capacidade de generalização. Para o problema contínuo o modelo abordado apresentou-se de forma satisfatória mediante o acréscimo de ruído. / Two trajectory planning problems are discussed in this work, one of them being discrete and the other continuous. The discrete problem consists in establishing all the intermediate states o f a trajectory to move a set of four blocks from a initial to a goal position. The continuous problem consists in planning and controlling the trajectory of the PUMA 560 mechanical arm. The class of models utilized in this work were the partially recurrent models. The discrete problem was used in order to compare the six proposed models, aiming at the acquisition of a model with a good performance for the resolution of production of temporal sequence problems. For the continuous problem, only the model that presented better performance in solving the discrete problem was applied. The initial and goal point are presented as input for the network in both problems. Two types of tests were applied to the architectures: production and generalization of temporal sequence tests. Four distinct types of trajectories with different complexity levels were created for each problem. In average, for the discrete problem, the architecture with feedback from the output to the input layer and from input layer to itself all-to-all presented the lowest epoch number in addition to the lowest error values during the training. This was the only model that managed to recover all the patterns trained and in general presented better generalization capacity. For this reason, this model was chosen to be applied in the resolution of the continuous problem. It presented a good performance to the production of mechanical arm trajectories, managing to reproduce the trained trajectories with great accuracy. For the discrete problem, all the models presented low generalization capacity. For the continuous problem, the approached model presented itself in a satisfactmy manner by means of noise addition.

Introduction: Tropical Cyclones (TCs) inflict considerable damage to life and property every year. A major problem is that residents often hesitate to follow evacuation orders when the early warning messages are perceived as inaccurate or uninformative. The root problem is that providing accurate early forecasts can be difficult, especially in countries with less economic and technical means. Aim: The aim of the thesis is to investigate how cyclone early warning systems can be technically improved. This means, first, identifying problems associated with the current cyclone early warning systems, and second, investigating if biologically based Artificial Neural Networks (ANNs) are feasible to solve some of the identified problems. Method: First, for evaluating the efficiency of cyclone early warning systems, Bangladesh was selected as study area, where a questionnaire survey and an in-depth interview were administered. Second, a review of currently operational TC track forecasting techniques was conducted to gain a better understanding of various techniques’ prediction performance, data requirements, and computational resource requirements. Third, a technique using biologically based ANNs was developed to produce TC track and intensity forecasts. Systematic testing was used to find optimal values for simulation parameters, such as feature-detector receptive field size, the mixture of unsupervised and supervised learning, and learning rate schedule. Five types of 2D data were used for training. The networks were tested on two types of novel data, to assess their generalization performance. Results: A major problem that is identified in the thesis is that the meteorologists at the Bangladesh Meteorological Department are currently not capable of providing accurate TC forecasts. This is an important contributing factor to residents’ reluctance to evacuate. To address this issue, an ANN-based TC track and intensity forecasting technique was developed that can produce early and accurate forecasts, uses freely available satellite images, and does not require extensive computational resources to run. Bidirectional connections, combined supervised and unsupervised learning, and a deep hierarchical structure assists the parallel extraction of useful features from five types of 2D data. The trained networks were tested on two types of novel data: First, tests were performed with novel data covering the end of the lifecycle of trained cyclones; for these test data, the forecasts produced by the networks were correct in 91-100% of the cases. Second, the networks were tested with data of a novel TC; in this case, the networks performed with between 30% and 45% accuracy (for intensity forecasts). Conclusions: The ANN technique developed in this thesis could, with further extensions and up-scaling, using additional types of input images of a greater number of TCs, improve the efficiency of cyclone early warning systems in countries with less economic and technical means. The thesis work also creates opportunities for further research, where biologically based ANNs can be employed for general-purpose weather forecasting, as well as for forecasting other severe weather phenomena, such as thunderstorms.

Activity recognition falls in general area of pattern recognition, but it resides mainly in temporal domain which leads to distinctive characteristics. We provide an extensive survey over existing tools including FSM, HMM, BNT, DBN, SCFG and Symbolic Network Approach (PNF-network). These tools are inefficient to meet many of the requirements of activity recognition, leading to this work to develop a new graphical model: Propagation Net (P-Net). Many activities can be represented by a partially ordered set of temporal intervals, each of which corresponds to a primitive motion. Each interval has both temporal and logical constraints that control the duration of the interval and its relationship with other intervals. P-Net takes advantage of such fundamental constraints that it provides an graphical conceptual model to describe the human knowledge and an efficient computational model to facilitate recognition and learning. P-Nets define an exponentially large joint distribution that standard bayesian inference cannot handle. We devise two approximation algorithms to interpret a multi-dimensional observation sequence of evidence as a multi-stream propagation process through P-Net. First, Local Maximal Search Algorithm (LMSA) is constructed with polynomial complexity; Second, we introduce a particle filter based framework, Discrete Condensation (D-Condensation) algorithm, which samples the discrete state space more efficiently then original Condensation. To construct a P-Net based system, we need two parts: P-Net and the corresponding detector set. Given topology information and detector library, P-Net parameters can be extracted easily from a relatively small number of positive examples. To avoid the tedious process of manually constructing the detector library, we introduce semi-supervised learning framework to build P-Net and the corresponding detectors together. Furthermore, we introduce the Contrast Boosting algorithm that forces the detectors to be as different as possible but not necessary to be non-overlapping. The classification and learning ability of P-Nets are verified on three data sets: 1)vision tracked indoor activity data set; 2)vision tracked glucose monitor calibration data set; 3)sensor data set on simple weight-lifting exercise. Comparison with standard SCFG and HMM prove a P-Net based system is easier to construct and has a superior ability to classify complex human activity and detect anomaly.

Depuis les travaux de Haiman (1985), l’iconicité de la syntaxe est un sujet à la mode. Ce sujet s’impose particulièrement dans le cas des langues isolantes, à morphologie réduite, où l’ordre des mots est le marqueur principal des structures syntaxiques et se trouve, par là, au centre de la grammaire. L’ordre des mots dans une phrase mime-t-il l’ordre des événements dont on parle ou reflète-t-il l’ordre même du discours, ou est-il arbitraire ? Dans la lignée des travaux sur l’iconicité de Peirce (1930), Haiman (1980, 1985), Tai (1985) etc., nous appelons ‘iconicité temporelle’ le fait que la succession dans le temps, c’est-à-dire dans la chaîne parlée, des constituants d’un énoncé mime la succession des événements dans un monde de référence. Nous avons étendu le champ d’application de cette ‘iconicité temporelle’ des événements aux procès et, de là, aux phases qui les composent. L’objectif de cette thèse est de tenter de ‘faire marcher’ l’idée d’‘iconicité de la séquence 'jusqu’au bout, en partant d’une définition des CVS la plus large possible permettant d’englober toute suite de constituants verbaux ne présentant aucun connecteur. Cela permet d’étendre l’étude à toute séquence de procès décomposable en sous-procès dans le monde de référence ou en sous-événements dans le monde du discours (systèmes protase-apodose hypothétique et temporel). Si l’iconicité est partout, c’est que les marques séquentielles (l’ordre des constituants), avec les informations sur les prédicats (valence et Aktionsart) codées dans le lexique, sont essentielles au fonctionnement des langues isolantes du type du chinois, et que ces marques séquentielles obéissent le plus souvent, au moins dans le cas du chinois, à l’iconicité. / Since Haiman (1985), the iconicity of syntax is a hot topic. This subject is particularly important in the case of isolating languages, with reduced morphology, in which the word order is the main marker of syntactic structures, and, is, therefore, at the centre of grammar. Does the word order in a sentence mimic the order of the events one is speaking of or does it reflect the very order of the discourse, or is it arbitrary? In the line of Peirce (1930), Haiman (1980, 1985), Tai (1985), etc., we call ‘temporal iconicity’ the fact that succession in the time, or in the spoken chain, of constituents of a statement mimics the succession of events in a world of reference. We have extended the scope of this ‘temporal iconicity’ from events to processes and hence to the phases that compose them. The objective of this thesis is to try to develop the idea of ‘iconicity of the temporal sequence’ to its very end, starting from a definition of SVC (serial verb construction) as wide as possible to encompass any sequence of verbal constituents without overt connector. In such a way, it becomes possible to extend the study to any sequence of decomposable processes in sub-tracks in the reference world or in sub-events in the discourse world (conditional and temporal protasis-apodosis systems). If the iconicity is everywhere, it is because that the sequential marks (the constituents order), with the informations about the predicates (valence and Aktionsart) encoded in the lexicon, are essential to the functioning of the isolating languages of the type of Chinese, and that these sequential marks obey most often, at least in the case of Chinese, to iconicity.

Cortical and subcortical microcircuits are continuously modified throughout life. Despite ongoing changes these networks stubbornly maintain their functions, which persist although destabilizing synaptic and nonsynaptic mechanisms should ostensibly propel them towards runaway excitation or quiescence. What dynamical phenomena exist to act together to balance such learning with information processing? What types of activity patterns do they underpin, and how do these patterns relate to our perceptual experiences? What enables learning and memory operations to occur despite such massive and constant neural reorganization? Progress towards answering many of these questions can be pursued through large-scale neuronal simulations.    In this thesis, a Hebbian learning rule for spiking neurons inspired by statistical inference is introduced. The spike-based version of the Bayesian Confidence Propagation Neural Network (BCPNN) learning rule involves changes in both synaptic strengths and intrinsic neuronal currents. The model is motivated by molecular cascades whose functional outcomes are mapped onto biological mechanisms such as Hebbian and homeostatic plasticity, neuromodulation, and intrinsic excitability. Temporally interacting memory traces enable spike-timing dependence, a stable learning regime that remains competitive, postsynaptic activity regulation, spike-based reinforcement learning and intrinsic graded persistent firing levels.    The thesis seeks to demonstrate how multiple interacting plasticity mechanisms can coordinate reinforcement, auto- and hetero-associative learning within large-scale, spiking, plastic neuronal networks. Spiking neural networks can represent information in the form of probability distributions, and a biophysical realization of Bayesian computation can help reconcile disparate experimental observations. / <p>QC 20170421</p>

The anomaly detection task is to recognize the presence of an unusual (and potentially hazardous) state within the behaviors or activities of a computer user, system, or network with respect to some model of normal behavior which may be either hard-coded or learned from observation. An anomaly detection agent faces many learning problems including learning from streams of temporal data, learning from instances of a single class, and adaptation to a dynamically changing concept. The domain is complicated by considerations of the trusted insider problem (recognizing the difference between innocuous and malicious behavior changes on the part of a trusted user). This study introduces the anomaly detection in web applications and formulates it as a machine learning task on temporal sequence data. In this study the goal is to develop a model or profile of normal working state of web application user and to detect anomalous conditions as deviations from the expected behavior patterns. We focus, here, on learning models of normality at the user behavioral level, as observed through a web application. In this study we introduce some sensors intended to function as a focus of attention unit at the lowest level of a classification hierarchy using Finite State Markov Chains and Hidden Markov Models and discuss the success of these sensors.

No description available.