<p> Social dynamics is concerned with the interactions of individuals and the resulting group behaviors. It models the temporal evolution of social systems via the interactions of the individuals within these systems. The availability of large-scale data in social networks and sensor networks offers an unprecedented opportunity to predict state changing events at the individual level. Examples of such events are disease infection, rumor propagation and opinion transition in elections, etc. Unlike previous research focusing on the collective effects of social systems, we want to make efficient inferences on the individual level.</p><p> Two main challenges are addressed: temporal modeling and computational complexity. The interaction pattern for each individual keeps changing over the time, i.e., an individual interacts with different individuals at different times. Second, as the number of tracked individual increases, the computational complexity grows exponentially with traditional sequential data analysis. </p><p> The contributions are: (i) leverage social networks and sensor networks data to make tractable inferences on both individual behaviors and collective effects in social dynamics. (ii) use the stochastic kinetic model to summarize dynamic interactions among individuals and simplify the state transition probabilities. (iii) propose an efficient variational inference algorithm whose complexity grows <i>linearly</i> with the number of tracked individuals <i> M</i>. Given the state space <i>K</i> of a single individual and the total number of time steps <i>T</i>, the complexity of naive brute-force approach is <i>O(K^MT)</i> and the complexity of existing exact inference approach is <i>O(K^MT)</i>. In comparison, the complexity of the proposed algorithm is<i> O(K²MT)</i>. In practice, it requires several iterations to converge. </p><p> In the empirical study concerning epidemics dynamics, given wireless sensor network data collected from more than ten thousand people (M = 13,888) over three years (T = 3465), we use the proposed algorithm to track disease transmission, and predict the probability of infection for each individual (K = 2) along the time until convergence (I=5). It is more efficient than state of the art sampling methods, i.e., MCMC and particle filter, while achieving high accuracy.</p>

Sentiment Analysis consists of recognizing sentiment orientation towards specific subjects within natural language texts. Most research in this area focuses on classifying documents as positive or negative. The purpose of this thesis is to quantitatively evaluate subjective opinions of customer reviews using a five star rating system, which is widely used on on-line review web sites, and to try to make the predicted score as accurate as possible. Firstly, this thesis presents two methods for rating reviews: classifying reviews by supervised learning methods as multi-class classification does, or rating reviews by using association scores of sentiment terms with a set of seed words extracted from the corpus, i.e. the unsupervised learning method. We extend the feature selection approach used in Turney's PMI-IR estimation by introducing semantic relatedness measures based up on the content of WordNet. This thesis reports on experiments using the two methods mentioned above for rating reviews using the combined feature set enriched with WordNet-selected sentiment terms. The results of these experiments suggest ways in which incorporating WordNet relatedness measures into feature selection may yield improvement over classification and unsupervised learning methods which do not use it. Furthermore, via ordinal meta-classifiers, we utilize the ordering information contained in the scores of bank reviews to improve the performance, we explore the effectiveness of re-sampling for reducing the problem of skewed data, and we check whether discretization benefits the ordinal meta-learning process. Finally, we combine the unsupervised and supervised meta-learning methods to optimize performance on our sentiment prediction task.

<p> Automatic age estimation from real-world and wild face images is a challenging task and has an increasing importance due to its wide range of applications in current and future lifestyles. As a result of increasing age specific human-computer interactions, it is expected that computerized systems should be capable of estimating the age from face images and respond accordingly. Over the past decade, many research studies have been conducted on automatic age estimation from face images. </p><p> In this research, new approaches for enhancing age classification of a person from face images based on deep neural networks (DNNs) are proposed. The work shows that pre-trained CNNs which were trained on large benchmarks for different purposes can be retrained and fine-tuned for age estimation from unconstrained face images. Furthermore, an algorithm to reduce the dimension of the output of the last convolutional layer in pre-trained CNNs to improve the performance is developed. Moreover, two new jointly fine-tuned DNNs frameworks are proposed. The first framework fine-tunes tow DNNs with two different feature sets based on the element-wise summation of their last hidden layer outputs. While the second framework fine-tunes two DNNs based on a new cost function. For both frameworks, each has two DNNs, the first DNN is trained by using facial appearance features that are extracted by a well-trained model on face recognition, while the second DNN is trained on features that are based on the superpixels depth and their relationships. </p><p> Furthermore, a new method for selecting robust features based on the power of DNN and <i>l₂₁-norm</i> is proposed. This method is mainly based on a new cost function relating the DNN and the L21 norm in one unified framework. To learn and train this unified framework, the analysis and the proof for the convergence of the new objective function to solve minimization problem are studied. Finally, the performance of the proposed jointly fine-tuned networks and the proposed robust features are used to improve the age estimation from the facial images. The facial features concatenated with their corresponding robust features are fed to the first part of both networks and the superpixels features concatenated with their robust features are fed to the second part of the network </p><p> Experimental results on a public database show the effectiveness of the proposed methods and achieved the state-of-art performance on a public database. </p><p>

A methodology for knowledge acquisition from terminology databases is presented. The methodology outlines how the content of a terminology database can be mapped onto a knowledge base with a minimum of human intervention. Typically, terms are defined and elaborated by terminologists by using sentences that have a common syntactic and semantic structure. It has been argued that in defining terms, terminologists use a local grammar and that this local grammar can be used to parse the definitions. The methodology has been implemented in a program called DEARSys (Definition Analysis and Representation System), that reads definition sentences and extracts new concepts and conceptual relations about the defined terms. The linguistic component of the system is a parser for the sublanguage of terminology definitions that analyses a definition into its logical form, which in turn is mapped onto a frame-based representation. The logical form is based on first-order logic (FOL) extended with untyped lambda calculus. Our approach is data-driven and domain independent; it has been applied to definitions of various domains. Experiments were conducted with human subjects to evaluate the information acquired by the system. The results of the preliminary evaluation were encouraging.

Artificial Neural Networks are massively parallel systems that are constructed from many simple processing elements called neurons. The neurons are connected via weights. This structure is inspired by the current understanding of how biological networks function. Since the 1980s, research into this field has exploded into the hive of activity that currently surrounds neural networks and intelligent systems. The work in this thesis is concerned with one particular artificial neural network: Adaptive Resonance Theory (ART). It is an unsupervised neural network that attempts to solve the stability-plasticity dilemma. The model is, however, limited by a few serious problems that restrict its use in real life situations. The network's ability to cluster consistently with uncorrupt inputs when the input is subject to even modest amounts of noise is severely handicapped. The work detailed herein attempts to improve on ART's behaviour towards noisy inputs. Novel equations are developed and described that improve on the network's performance when the system is subject to noisy inputs. One of the novel equations affecting vigilance makes a significant improvement over the originators' equations and can cope with 16% target noise before results fall to the same values as the standard equation. The novel work is tested using a real-life (not simulated) data set from the MSTAR database. Synthetic Aperture Radar targets are clustered and then subject to noise before being represented to the network. These data simulate a typical environment where a clustering or classifying module would be needed for object recognition. Such a module could then be used in an Automatic Target Recognition (ATR) system. Once the problem is mitigated, Adaptive Resonance Theory neural networks could play important roles in ATR systems due to its lack of computational complexity and low memory requirements when compared with other clustering techniques. Keywords: Adaptive Resonance Theory, clustering consistency, neural network, automatic target recognition, noisy inputs.

A genetic algorithm has been proposed as a computational method for producing molecular mechanics force field parameters, using input data from the Cambridge Structural Database. The method has been applied initially to simple test data and to a coordination compound under various conditions and the results have been analysed in an attempt to determine the most suitable operating parameters. Finally, several possible approaches, both software and hardware, aimed towards improving the algorithm's performance, are discussed. Two approaches for extending the performance of a PC have been considered, namely upgrading the computational power and the graphics capabilities using state-of-the-art hardware solutions. Both of these features can be considered essential for crystal modelling. Conclusions have then been drawn regarding the applicability of these approaches to a modern, top-of-the-range PC. Finally, a variety of software modules are proposed, aimed at the 'engineering' of known crystal structures. Many of these techniques are graphical in nature, enabling the visualisation and manipulation of the inherent symmetry these systems display.

<p> At any given moment, the mind needs to decide <i>how</i> to think about <i>what</i>, and for <i>how long</i>. The mind's ability to manage itself is one of the hallmarks of human cognition, and these meta-level questions are crucially important to understanding how cognition is so fluid and flexible across so many situations. In this thesis, I investigate the problem of cognitive resource management by focusing in particular on the domain of <i>mental simulation</i>. Mental simulation is a phenomenon in which people can perceive and manipulate objects and scenes in their imagination in order to make decisions, predictions, and inferences about the world. Importantly, if thinking is computation, then mental simulation is one particular type of computation analogous to having a rich, forward model of the world. </p><p> Given access to such a model as rich and flexible as mental simulation, how should the mind use it? How does the mind infer anything from the outcomes of its simulations? How many resources should be allocated to running which simulations? When should such a rich forward model be used in the first place, in contrast to other types of computation such as heuristics or rules? Understanding the answers to these questions provides broad insight into people's meta-level reasoning because mental simulation is involved in almost every aspect of cognition, including perception, memory, planning, physical reasoning, language, social cognition, problem solving, scientific reasoning, and even creativity. Through a series of behavioral experiments combined with machine learning models, I show how people adaptively use their mental simulations to learn new things about the world; that they choose which simulations to run based on which they think will be more informative; and that they allocate their cognitive resources to spend less time on easy problems and more time on hard problems.</p><p>

<p> Historically, most virtual human character research focuses on realism/emotions, interaction with humans, and discourse. The majority of the spatial positioning of characters has focused on one-on-one conversations with humans or placing virtual characters side-by-side when talking. These rely on conversation space as the main driver (if any) for character placement.</p><p> Movies and games rely on motion capture (mocap) files and hard-coded functions to perform spatial movements. These require extensive technical knowledge just to have a character move from one place to another. Other methods involve the use of Behavior Markup Language (BML), a form of XML, which describes character behaviors. BML Realizers take this BML and perform the requested behavior(s) on the character(s). Also, there are waypoint and other spatial navigation schemes, but they primarily focus on traversals and not correct positioning. Each of these require a fair amount of low-level detail and knowledge to write, plus BML realizers are still in their early stages of development. </p><p> Theatre, movies, and television all utilize a form of play-scripts, which provide detailed information on what the actor must do spatially, and when for a particular scene (that is spatio-temporal direction). These involve annotations, in addition to the speech, which identify scene setups, character movements, and entrances /exits. Humans have the ability to take these play-scripts and easily perform a believable scene. </p><p> This research focuses on utilizing play-scripts to provide spatio-temporal direction to virtual characters within a scene. Because of the simplicity of creating a playscript, and our algorithms to interpret the scripts, we are able to provide a quick method of blocking scenes with virtual characters.</p><p> We focus on not only an all-virtual cast of characters, but also human-controlled characters intermixing with the virtual characters for the scene. The key here is that human-controlled characters introduce a dynamic spatial component that affects how the virtual characters should perform the scene to ensure continuity, cohesion, and inclusion with the human-controlled character.</p><p> The algorithms to accomplish the blocking of a scene from a standard play-script are the core research contribution. These techniques include some part of speech tagging, named entity recognition, a rules engine, and strategically designed force-directed graphs. With these methods, we are able to similarly map any play-script&rsquo;s spatial positioning of characters to a human-performed version of the same playscript. Also, human-based evaluations indicate these methods provide a qualitatively good performance.</p><p> Potential applications include: a rehearsal tool for actors; a director tool to help create a play-script; a controller for virtual human characters in games or virtual environments; or a planning tool for positioning people in an industrial environment.</p><p>

<p> Natural Language Understanding (NLU) has been one of the longest-running and the most challenging areas in artificial intelligence. For any natural language comprehension system having a basic understanding of entities and concepts is a primary requirement. Comparison, where we name the similarities and differences between entities and concepts, is a unique cognitive ability in humans which requires memorizing facts, experiencing things and integration of concepts of the world. Clearly, developing NLU systems that are capable of comprehending comparison is a crucial step forward in AI. In this thesis, I will present my research on developing systems that are capable of comprehending comparison, through which, systems can learn world knowledge and perform basic commonsense reasoning.</p><p>

<p> Building systems that have natural language understanding capabilities has been one of the oldest and the most challenging pursuits in AI. In this thesis, we present our research on modeling language in terms of `events' and how they interact with each other in time, mainly in the domain of stories. </p><p> Deep language understanding, which enables inference and commonsense reasoning, requires systems that have large amounts of knowledge which would enable them to connect surface language to the concepts of the world. A part of our work concerns developing approaches for learning semantically rich knowledge bases on events. First, we present an approach to automatically acquire conceptual knowledge about events in the form of inference rules, which can enable commonsense reasoning. We show that the acquired knowledge is precise and informative which can be employed in different NLP tasks. </p><p> Learning stereotypical structure of related events, in the form of narrative structures or scripts, has been one of the major goals in AI. The research on narrative understanding has been hindered by the lack of a proper evaluation framework. We address this problem by introducing a new framework for evaluating story understanding and script learning: the 'Story Cloze Test (SCT)&rsquo;. In this test, the system is posed with a short four-sentence narrative context along with two alternative endings to the story, and is tasked with choosing the right ending. Along with the SCT, We have worked on developing the ROCStories corpus of about 100K commonsense short stories, which enables building models for story understanding and story generation. We present various models and baselines for tackling the task of SCT and show that human can perform with an accuracy of 100%. </p><p> One prerequisite for understanding and proper modeling of events and their interactions is to develop a comprehensive semantic framework for representing their variety of relations. We introduce `Causal and Temporal Relation Scheme (CaTeRS)' which is a rich semantic representation for event structures, with an emphasis on the domain of stories. The impact of the SCT and the ROCStories project goes beyond this thesis, where numerous teams and individuals across academia and industry have been using the evaluation framework and the dataset for a variety of purposes. We hope that the methods and the resources presented in this thesis will spur further research on building systems that can effectively model eventful context, understand, and generate logically-sound stories. </p><p>