In this research, a novel machine learning method is designed and applied to Mine Countermeasure Missions. Similarly to some kernel methods, the proposed approach seeks to compute a linear model from another higher dimensional feature space. However, no kernel is used and the feature mapping is explicit. Computation can be done directly in the accessible feature space. In the proposed approach, the feature projection is implemented by constructing a large hidden layer, which differs from traditional belief that Multi-Layer Perceptron is usually funnel-shaped and the hidden layer is used as feature extractor. The proposed approach is a general method that can be applied to various problems. It is able to improve the performance of the neural network based methods and the learning speed of support vector machine. The classification speed of the proposed approach is also faster than that of kernel machines on the mine countermeasure mission task.

Over the last two decades, the field of educational data mining (EDM) has been focusing on predicting the correctness of the next student response to the question (e.g., [2, 6] and the 2010 KDD Cup), in other words, predicting student short-term performance. Student modeling has been widely used for making such inferences. Although performing well on the immediate next problem is an indicator of mastery, it is by far not the only criteria. For example, the Pittsburgh Science of Learning Center's theoretic framework focuses on robust learning (e.g., [7, 10]), which includes the ability to transfer knowledge to new contexts, preparation for future learning of related skills, and retention - the ability of students to remember the knowledge they learned over a long time period. Especially for a cumulative subject such as mathematics, robust learning, particularly retention, is more important than short-term indicators of mastery. The Automatic Reassessment and Relearning System (ARRS) is a platform we developed and deployed on September 1st, 2012, which is mainly used by middle-school math teachers and their students. This system can help students better retain knowledge through automatically assigning tests to students, giving students opportunity to relearn the skill when necessary and generating reports to teachers. After we deployed and tested the system for about seven months, we have collected 287,424 data points from 6,292 students. We have created several models that predict students' retention performance using a variety of features, and discovered which were important for predicting correctness on a delayed test. We found that the strongest predictor of retention was a student's initial speed of mastering the content. The most striking finding was that students who struggled to master the content (took over 8 practice attempts) showed very poor retention, only 55% correct, after just one week. Our results will help us advance our understanding of learning and potentially improve ITS.

In this research, a novel machine learning method is designed and applied to Mine Countermeasure Missions. Similarly to some kernel methods, the proposed approach seeks to compute a linear model from another higher dimensional feature space. However, no kernel is used and the feature mapping is explicit. Computation can be done directly in the accessible feature space. In the proposed approach, the feature projection is implemented by constructing a large hidden layer, which differs from traditional belief that Multi-Layer Perceptron is usually funnel-shaped and the hidden layer is used as feature extractor. The proposed approach is a general method that can be applied to various problems. It is able to improve the performance of the neural network based methods and the learning speed of support vector machine. The classification speed of the proposed approach is also faster than that of kernel machines on the mine countermeasure mission task.

In this research, a novel machine learning method is designed and applied to Mine Countermeasure Missions. Similarly to some kernel methods, the proposed approach seeks to compute a linear model from another higher dimensional feature space. However, no kernel is used and the feature mapping is explicit. Computation can be done directly in the accessible feature space. In the proposed approach, the feature projection is implemented by constructing a large hidden layer, which differs from traditional belief that Multi-Layer Perceptron is usually funnel-shaped and the hidden layer is used as feature extractor. The proposed approach is a general method that can be applied to various problems. It is able to improve the performance of the neural network based methods and the learning speed of support vector machine. The classification speed of the proposed approach is also faster than that of kernel machines on the mine countermeasure mission task.

Obtaining ground-truth label information from real-world data along with uncertainty quantification can be challenging or even infeasible. In the absence of labeled data for a certain task, unsupervised domain adaptation (UDA) techniques have shown great accomplishment by learning transferable knowledge from labeled source domain data and adapting it to unlabeled target domain data, yet uncertainties are still a big concern under domain shifts. Distributionally robust learning (DRL) is emerging as a high-potential technique for building reliable learning systems that are robust to distribution shifts. In this research, a distributionally robust unsupervised domain adaptation (DRUDA) method is proposed to enhance the machine learning model generalization ability under input space perturbations. The DRL-based UDA learning scheme is formulated as a min-max optimization problem by optimizing worst-case perturbations of the training source data. Our Wasserstein distributionally robust framework can reduce the shifts in the joint distributions across domains. The proposed DRUDA method has been tested on various benchmark datasets. In addition, a gradient mapping-guided explainable network (GMGENet) is proposed to analyze 3D medical images for extracapsular extension (ECE) identification. DRUDA-enhanced GMGENet is evaluated, and experimental results demonstrate that the proposed DRUDA improves transfer performance on target domains for the 3D image analysis task successfully. This research enhances the understanding of distributionally robust optimization in domain adaptation and is expected to advance the current unsupervised machine learning techniques.

MATTOS, C. L. C. Recurrent gaussian processes and robust dynamical modeling. 2017. 189 f. Tese (Doutorado em Engenharia de Teleinformática)–Centro de Tecnologia, Universidade Federal do Ceará, Fortaleza, 2017. / Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-09T02:26:38Z No. of bitstreams: 1 2017_tes_clcmattos.pdf: 5961013 bytes, checksum: fc44d8b852e28fa0e1ebe0c87389c0da (MD5) / Rejected by Marlene Sousa (mmarlene@ufc.br), reason: Prezado César; Prezado Pedro: Existe uma orientação para que normalizemos as dissertações e teses da UFC, em suas paginas pré-textuais e lista de referencias, pelas regras da ABNT. Por esse motivo, sugerimos consultar o modelo de template, para ajudá-lo nesta tarefa, disponível em: http://www.biblioteca.ufc.br/educacao-de-usuarios/templates/ Vamos agora as correções sempre de acordo com o template: 1. A partir da folha de aprovação as informações devem ser em língua inglesa. 2. A dedicatória deve ter a distancia até o final da folha observado. Veja no guia www.bibliotecas.ufc.br 3. A epígrafe deve ter a distancia até o final da folha observado. Veja no guia www.bibliotecas.ufc.br 4. As palavras List of Figures, LIST OF ALGORITHMS, List of Tables, Não devem ter caixa delimitando e nem ser na cor vermelha. 5. O sumário Não deve ter caixa delimitando e nem ser na cor vermelha. Nas seções terciárias, os dígitos também ficam em itálico. Os Apêndices e seus títulos, devem ficar na mesma margem da Palavra Referencias e devem iniciar com APENDICE A - Seguido do titulo. Após essas correções, enviaremos o nada consta por e-mail. Att. Marlene Rocha mmarlene@ufc.br on 2017-09-11T13:44:25Z (GMT) / Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-11T20:04:00Z No. of bitstreams: 1 2017_tes_clcmattos.pdf: 6102703 bytes, checksum: 34d9e125c70f66ca9c095e1bc6bfb7e7 (MD5) / Rejected by Marlene Sousa (mmarlene@ufc.br), reason: Lincoln, Falta apenas vc colocar no texto em português a palavra RESUMO (nesse caso não é traduzido pois se refere ao resumo em língua portuguesa) pois vc colocou ABSTRACT duas vezes para o texto em português e inglês. on 2017-09-12T11:06:29Z (GMT) / Submitted by Renato Vasconcelos (ppgeti@ufc.br) on 2017-09-12T14:05:11Z No. of bitstreams: 1 2017_tes_clcmattos.pdf: 6102699 bytes, checksum: 0a85b8841d77f0685b1153ee8ede0d85 (MD5) / Approved for entry into archive by Marlene Sousa (mmarlene@ufc.br) on 2017-09-12T16:29:17Z (GMT) No. of bitstreams: 1 2017_tes_clcmattos.pdf: 6102699 bytes, checksum: 0a85b8841d77f0685b1153ee8ede0d85 (MD5) / Made available in DSpace on 2017-09-12T16:29:18Z (GMT). No. of bitstreams: 1 2017_tes_clcmattos.pdf: 6102699 bytes, checksum: 0a85b8841d77f0685b1153ee8ede0d85 (MD5) Previous issue date: 2017-08-25 / The study of dynamical systems is widespread across several areas of knowledge. Sequential data is generated constantly by different phenomena, most of them we cannot explain by equations derived from known physical laws and structures. In such context, this thesis aims to tackle the task of nonlinear system identification, which builds models directly from sequential measurements. More specifically, we approach challenging scenarios, such as learning temporal relations from noisy data, data containing discrepant values (outliers) and large datasets. In the interface between statistics, computer science, data analysis and engineering lies the machine learning community, which brings powerful tools to find patterns from data and make predictions. In that sense, we follow methods based on Gaussian Processes (GP), a principled, practical, probabilistic approach to learning in kernel machines. We aim to exploit recent advances in general GP modeling to bring new contributions to the dynamical modeling exercise. Thus, we propose the novel family of Recurrent Gaussian Processes (RGPs) models and extend their concept to handle outlier-robust requirements and scalable stochastic learning. The hierarchical latent (non-observed) structure of those models impose intractabilities in the form of non-analytical expressions, which are handled with the derivation of new variational algorithms to perform approximate deterministic inference as an optimization problem. The presented solutions enable uncertainty propagation on both training and testing, with focus on free simulation. We comprehensively evaluate the proposed methods with both artificial and real system identification benchmarks, as well as other related dynamical settings. The obtained results indicate that the proposed approaches are competitive when compared to the state of the art in the aforementioned complicated setups and that GP-based dynamical modeling is a promising area of research. / O estudo dos sistemas dinâmicos encontra-se disseminado em várias áreas do conhecimento. Dados sequenciais são gerados constantemente por diversos fenômenos, a maioria deles não passíveis de serem explicados por equações derivadas de leis físicas e estruturas conhecidas. Nesse contexto, esta tese tem como objetivo abordar a tarefa de identificação de sistemas não lineares, por meio da qual são obtidos modelos diretamente a partir de observações sequenciais. Mais especificamente, nós abordamos cenários desafiadores, tais como o aprendizado de relações temporais a partir de dados ruidosos, dados contendo valores discrepantes (outliers) e grandes conjuntos de dados. Na interface entre estatísticas, ciência da computação, análise de dados e engenharia encontra-se a comunidade de aprendizagem de máquina, que fornece ferramentas poderosas para encontrar padrões a partir de dados e fazer previsões. Nesse sentido, seguimos métodos baseados em Processos Gaussianos (PGs), uma abordagem probabilística prática para a aprendizagem de máquinas de kernel. A partir de avanços recentes em modelagem geral baseada em PGs, introduzimos novas contribuições para o exercício de modelagem dinâmica. Desse modo, propomos a nova família de modelos de Processos Gaussianos Recorrentes (RGPs, da sigla em inglês) e estendemos seu conceito para lidar com requisitos de robustez a outliers e aprendizagem estocástica escalável. A estrutura hierárquica e latente (não-observada) desses modelos impõe expressões não- analíticas, que são resolvidas com a derivação de novos algoritmos variacionais para realizar inferência determinista aproximada como um problema de otimização. As soluções apresentadas permitem a propagação da incerteza tanto no treinamento quanto no teste, com foco em realizar simulação livre. Nós avaliamos em detalhe os métodos propostos com benchmarks artificiais e reais da área de identificação de sistemas, assim como outras tarefas envolvendo dados dinâmicos. Os resultados obtidos indicam que nossas propostas são competitivas quando comparadas ao estado da arte, mesmo nos cenários que apresentam as complicações supracitadas, e que a modelagem dinâmica baseada em PGs é uma área de pesquisa promissora.

The goal of Intelligent Tutoring systems (ITSs) is to engage the students in sustained reasoning activity and to interact with students based on a deep understanding of student behavior. In order to understand student behavior, ITSs rely on student modeling methods to observes student actions in the tutor and creates a quantitative representation of student knowledge, interests, affective states. Good student models are going to effectively help ITSs customize instructions, engage student's interest and then promote learning. Thus, the work of building ITSs and advancing student modeling should be considered as two interconnected components of one system rather than two separate topics. In this work, we utilized the theoretical support of a well-known learning science theory, the spacing effect, to guide the development of an ITS, called Automatic Reassessment and Relearning System (ARRS). ARRS not only validated the effectiveness of spacing effect, but it also served as a testing field which allowed us to find out new approaches to improve student learning by conducting large-scale randomized controlled trials (RCTs). The rich data set we gathered from ARRS has advanced our understanding of robust learning and helped us build student models with advanced data mining methods. At the end, we designed a set of API that supports the development of ARRS in next generation ASSISTments platform and adopted deep learning algorithms to further improve retention performance prediction. We believe our work is a successful example of combining theory and practice to advance science and address real- world problems.

The distributed nature of Federated Learning (FL) creates security-related vulnerabilities including training-time attacks. Recently, it has been shown that well-known Byzantine-resilient aggregation schemes are indeed vulnerable to an informed adversary who has access to the aggregation scheme and updates sent by clients. Therefore, it is a significant challenge to establish successful defense mechanisms against such an adversary. To the best of our knowledge, most current aggregators are immune to single or partial attacks and none of them is expandable to defend against new attacks. We frame the robust distributed learning problem as a game between a server and an adversary that tailors training-time attacks. We introduce RobustTailor, a simulation-based algorithm that prevents the adversary from being omniscient. RobustTailor is a mixed strategy and has good expandability for any deterministic Byzantine-resilient algorithm. Under a challenging setting with information asymmetry between two players, we show that our method enjoys theoretical guarantees in terms of regret bounds. RobustTailor preserves almost the same privacy guarantees as standard FL and robust aggregation schemes. Simulation improves robustness to training-time attacks significantly. Empirical results under challenging attacks validate our theory and show that RobustTailor preforms similar to an upper bound which assumes the server has perfect knowledge of all honest clients over the course of training. / Den distribuerade karaktären hos federerade maskininlärnings-system gör dem sårbara för cyberattacker, speciellt under tiden då systemen tränas. Nyligen har det visats att många existerande Byzantine-resilienta aggregeringssystem är sårbara för attacker från en välinformerad motståndare som har tillgång till aggregeringssystemet och uppdateringarna som skickas av klienterna. Det är därför en stor utmaning att skapa framgångsrika försvarsmekanismer mot en sådan motståndare. Såvitt vi vet är de flesta nuvarande aggregatorer immuna mot enstaka eller partiella attacker och ingen av dem kan på ett enkelt sätt utvidgas för att försvara sig mot nya attacker. Vi utformar det robusta distribuerade inlärningsproblemet som ett spel mellan en server och en motståndare som skräddarsyr attacker under träningstiden. Vi introducerar RobustTailor, en simuleringsbaserad algoritm som förhindrar att motståndaren är allvetande. RobustTailor är en blandad strategi med god expanderbarhet för alla deterministiska Byzantine-resilienta algoritmer. I en utmanande miljö med informationsasymmetri mellan de två spelarna visar vi att vår metod har teoretiska garantier i form av gränser för ånger. RobustTailor har nästan samma integritetsgarantier som standardiserade federerade inlärnings- och robusta aggregeringssystem. Vi illustrerar även hur simulering förbättrar robustheten mot attacker under träningstiden avsevärt. Empiriska resultat vid utmanande attacker bekräftar vår teori och visar att RobustTailor presterar på samma sätt som en övre gräns som förutsätter att servern har perfekt kunskap om alla ärliga klienter under utbildningens gång.

<p>In this thesis, we present algorithms to allow agents to estimate certain properties in a robust, online, and distributed manner. Each agent receives a sequence of observations, and through communication, collectively infers properties of the data gathered by all agents by communicating.</p> <p><br></p> <p>In the first part of the thesis, we provide algorithms to infer the correlations between interacting entities from these large datasets. Gaussian graphical models have been well studied to represent the relationships between the various random variables which generate data, and numerous algorithms have been proposed to learn the dependencies in such models. However, existing algorithms typically process data in a batch at a central location, limiting their applications in scenarios where data arrive in real-time and are gathered by different agents.  </p> <p><br></p> <p>To address these challenges, first, we propose an online sparse inverse covariance algorithm to infer the static network structure (i.e., dependencies between nodes) in real-time from time-series data, in a centralized location. Subsequently, we propose a distributed algorithm to cooperatively learn the network structure in real-time from data collected by distributed agents. We characterize the theoretical convergence properties and provide simulations using synthetic datasets and real-world hurricane Twitter datasets in disaster management applications.    </p> <p><br></p> <p>The second part of this thesis addresses the robustness of online and distributed learning under arbitrary data corruption. We propose online and distributed algorithms for robust mean, covariance, and sparse inverse covariance estimation. These algorithms are capable of operating effectively even in the presence of adversarial data attacks. We provide theoretical bounds on the error and rate of convergence of these methods and evaluate their performance under various settings.</p> <p><br></p> <p>Finally, we consider the problem of classification with a network of heterogeneous and partially informative agents, each receiving local data from an underlying true class, and equipped with a classifier that only distinguishes between a subset of the entire set of classes. We propose an iterative algorithm that uses the posterior probabilities of any classifier and recursively updates each agent's local belief based on its local signals and belief information from its neighbors. We then adopt a novel distributed min-rule to update each agent’s global belief and enable learning of the true class for all agents. We analyze the convergence properties of our proposed algorithm, and subsequently, demonstrate and compare its performance with local averaging and global average consensus through simulations and with a visual image dataset.</p>