Surrogate models are indispensable in the analysis of engineering systems. The quality of surrogate models is determined by the data quality and the model class but achieving a high standard of them is challenging in complex engineering systems. Heterogeneity, implicit constraints, and extreme events are typical examples of the factors that complicate systems, yet they have been underestimated or disregarded in machine learning. This dissertation is dedicated to tackling the challenges in surrogate modeling of complex engineering systems by developing the following machine learning methodologies. (i) Partitioned active learning partitions the design space according to heterogeneity in response features, thereby exploiting localized models to measure the informativeness of unlabeled data. (ii) For the systems with implicit constraints, failure-averse active learning incorporates constraint outputs to estimate the safe region and avoid undesirable failures in learning the target function. (iii) The multi-output extreme spatial learning enables modeling and simulating extreme events in composite fuselage assembly. The proposed methods were applied to real-world case studies and outperformed benchmark methods. / Doctor of Philosophy / Data-driven decisions are ubiquitous in the engineering domain, in which data-driven models are fundamental. Active learning is a subdomain in machine learning that enables data-efficient modeling, and extreme spatial modeling is suitable for analyzing rare events. Although they are superb techniques for data-driven modeling, existing methods thereof cannot effectively address modern engineering systems complicated by heterogeneity, implicit constraints, and rare events. This dissertation is dedicated to advancing active learning and extreme spatial modeling for complex engineering systems by proposing three methodologies. The first method is partitioned active learning that efficiently learns systems, changing their behaviors, by localizing the information measurement. Second, failure-averse active learning is established to learn systems subject to implicit constraints, which cannot be analytically solved, and to minimize constraint violations. Lastly, the multi-output extreme spatial model is developed to model and simulate rare events that are associated with extremely large values in the aircraft manufacturing system. The proposed methods overcome the limitations of existing methods and outperform benchmark methods in the case studies.

This study investigated the effect of inquiry-based instruction in technical undergraduate education. Specifically, the effect was measured along two dimensions: 1) the effect on student learning and, 2) student attitude towards subject matter. The researcher designed an inquiry-based instructional approach to encourage interaction between teacher and students and to help students take more responsibility for their learning. Three technical undergraduate classes participated in the study. Each class was divided into experimental and control groups. For the experimental group, a twice-a-week traditional lecture was replaced with a once-a-week inquiry-based question and answer session. Students in the control group were taught as normal, by a traditional style lecture. Students in the experimental group were expected to use the extra hour, gained by meeting only once once-a-week, to study and prepare. Both groups were administered pre- and post- tests to determine the learning that took place during the experimental intervention. Pre- and post- surveys were also administered to assess the effect of the inquiry-based instruction on student attitude. Additionally, scores from student exams, professor surveys, and researcher observations were used to collect data and understand the effect of the instructional approach. The findings suggest that inquiry-based learning in technical classes can have a positive effect on learning and attitude.

In this paper, we propose a novel active learning algorithm for short-text (Chinese) classification applied to a deep learning architecture. This topic thus belongs to a cross research area between active learning and deep learning. One of the bottlenecks of deeplearning for classification is that it relies on large number of labeled samples, which is expensive and time consuming to obtain. Active learning aims to overcome this disadvantage through asking the most useful queries in the form of unlabeled samples to belabeled. In other words, active learning intends to achieve precise classification accuracy using as few labeled samples as possible. Such ideas have been investigated in conventional machine learning algorithms, such as support vector machine (SVM) for imageclassification, and in deep neural networks, including convolutional neural networks (CNN) and deep belief networks (DBN) for image classification. Yet the research on combining active learning with recurrent neural networks (RNNs) for short-text classificationis rare. We demonstrate results for short-text classification on datasets from Zhuiyi Inc. Importantly, to achieve better classification accuracy with less computational overhead,the proposed algorithm shows large reductions in the number of labeled training samples compared to random sampling. Moreover, the proposed algorithm is a little bit better than the conventional sampling method, uncertainty sampling. The proposed activelearning algorithm dramatically decreases the amount of labeled samples without significantly influencing the test classification accuracy of the original RNNs classifier, trainedon the whole data set. In some cases, the proposed algorithm even achieves better classification accuracy than the original RNNs classifier. / I detta arbete studerar vi en ny aktiv inlärningsalgoritm som appliceras på en djup inlärningsarkitektur för klassificering av korta (kinesiska) texter. Ämnesområdet hör därmedtill ett ämnesöverskridande område mellan aktiv inlärning och inlärning i djupa nätverk .En av flaskhalsarna i djupa nätverk när de används för klassificering är att de beror avtillgången på många klassificerade datapunkter. Dessa är dyra och tidskrävande att skapa. Aktiv inlärning syftar till att överkomma denna typ av nackdel genom att generera frågor rörande de mest informativa oklassade datapunkterna och få dessa klassificerade. Aktiv inlärning syftar med andra ord till att uppnå bästa klassificeringsprestanda medanvändandet av så få klassificerade datapunkter som möjligt. Denna idé har studeratsinom konventionell maskininlärning, som tex supportvektormaskinen (SVM) för bildklassificering samt inom djupa neuronnätverk inkluderande bl.a. convolutional networks(CNN) och djupa beliefnetworks (DBN) för bildklassificering. Emellertid är kombinationenav aktiv inlärning och rekurrenta nätverk (RNNs) för klassificering av korta textersällsynt. Vi demonstrerar här resultat för klassificering av korta texter ur en databas frånZhuiyi Inc. Att notera är att för att uppnå bättre klassificeringsnoggranhet med lägre beräkningsarbete (overhead) så uppvisar den föreslagna algoritmen stora minskningar i detantal klassificerade träningspunkter som behövs jämfört med användandet av slumpvisadatapunkter. Vidare, den föreslagna algoritmen är något bättre än den konventionellaurvalsmetoden, osäkherhetsurval (uncertanty sampling). Den föreslagna aktiva inlärningsalgoritmen minska dramatiskt den mängd klassificerade datapunkter utan att signifikant påverka klassificeringsnoggranheten hos den ursprungliga RNN-klassificeraren när den tränats på hela datamängden. För några fall uppnår den föreslagna algoritmen t.o.m.bättre klassificeringsnoggranhet än denna ursprungliga RNN-klassificerare.

No description available.

With the proliferation of social media, gathering data has became cheaper and easier than before. However, this data can not be used for supervised machine learning without labels. Asking experts to annotate sufficient data for training is both expensive and time-consuming. Current techniques provide two solutions to reducing the cost and providing sufficient labels: crowdsourcing and active learning. Crowdsourcing, which outsources tasks to a distributed group of people, can be used to provide a large quantity of labels but controlling the quality of labels is hard. Active learning, which requires experts to annotate a subset of the most informative or uncertain data, is very sensitive to the annotation errors. Though these two techniques can be used independently of one another, by using them in combination they can complement each other’s weakness. In this thesis, I investigate the development of active learning Support Vector Machines (SVMs) and expand this model to sequential data. Then I discuss the weakness of combining active learning and crowdsourcing, since the active learning is very sensitive to low quality annotations which are unavoidable for labels collected from crowdsourcing. In this thesis, I propose three possible strategies, incremental relabeling, importance-weighted label prediction and active Bayesian Networks. The incremental relabeling strategy requires workers to devote more annotations to uncertain samples, compared to majority voting which allocates different samples the same number of labels. Importance-weighted label prediction employs an ensemble of classifiers to guide the label requests from a pool of unlabeled training data. An active learning version of Bayesian Networks is used to model the difficulty of samples and the expertise of workers simultaneously to evaluate the relative weight of workers’ labels during the active learning process. All three strategies apply different techniques with the same expectation – identifying the optimal solution for applying an active learning model with mixed label quality to iii crowdsourced data. However, the active Bayesian Networks model, which is the core element of this thesis, provides additional benefits by estimating the expertise of workers during the training phase. As an example application, I also demonstrate the utility of crowdsourcing for human activity recognition problems.

The purpose of this study is to review material from the scientific field of psychology and where appropriate adapt it to experiential and active learning classroom experiences. The study is conducted in order to meet the Swedish curriculum for gymnasium and the courses Psychology 1 and 2. The review includes scientific material in a range of forms, such as training programs, personal- and school intervention programs, psychometrics and experimental psychology. The study suggests classroom activities on the topics:  cognitive-behavioral therapy, stress coping, positive psychology, emotional intelligence, psychometrics, cultural competency and cognitive bias. / Syftet med denna studie är att gå igenom material från det vetenskapliga fältet psykologi och där det är lämpligt anpassa det till klassrumsövningar som använder sig av upplevelsebaserat och aktivt lärande. Studien genomfördes med syftet att uppfylla den svenska läroplanen för gymnasiet och kurserna Psykologi 1 och 2. Undersökningen byggde på vetenskapligt material i olika former inkluderat träningsprogram, åtgärdsprogram för individer och skolor, psykometri och experimentell psykologi. Studien föreslår klassrumsövningar i ämnena: kognitiv beteendeterapi, stresshantering, positiv psykologi, emotionell intelligens, psykometri, kulturell kompetens och kognitiv bias.

Deep Gaussian processes (DGPs) upgrade ordinary GPs through functional composition, in which intermediate GP layers warp the original inputs, providing flexibility to model non-stationary dynamics. Recent applications in machine learning favor approximate, optimization-based inference for fast predictions, but applications to computer surrogate modeling - with an eye towards downstream tasks like Bayesian optimization and reliability analysis - demand broader uncertainty quantification (UQ). I prioritize UQ through full posterior integration in a Bayesian scheme, hinging on elliptical slice sampling of latent layers. I demonstrate how my DGP's non-stationary flexibility, combined with appropriate UQ, allows for active learning: a virtuous cycle of data acquisition and model updating that departs from traditional space-filling designs and yields more accurate surrogates for fixed simulation effort. I propose new sequential design schemes that rely on optimization of acquisition criteria through evaluation of strategically allocated candidates instead of numerical optimizations, with a motivating application to contour location in an aeronautics simulation. Alternatively, when simulation runs are cheap and readily available, large datasets present a challenge for full DGP posterior integration due to cubic scaling bottlenecks. For this case I introduce the Vecchia approximation, popular for ordinary GPs in spatial data settings. I show that Vecchia-induced sparsity of Cholesky factors allows for linear computational scaling without compromising DGP accuracy or UQ. I vet both active learning and Vecchia-approximated DGPs on numerous illustrative examples and real computer experiments. I provide open-source implementations in the "deepgp" package for R on CRAN. / Doctor of Philosophy / Scientific research hinges on experimentation, yet direct experimentation is often impossible or infeasible (practically, financially, or ethically). For example, engineers designing satellites are interested in how the shape of the satellite affects its movement in space. They cannot create whole suites of differently shaped satellites, send them into orbit, and observe how they move. Instead they rely on carefully developed computer simulations. The complexity of such computer simulations necessitates a statistical model, termed a "surrogate", that is able to generate predictions in place of actual evaluations of the simulator (which may take days or weeks to run). Gaussian processes (GPs) are a common statistical modeling choice because they provide nonlinear predictions with thorough estimates of uncertainty, but they are limited in their flexibility. Deep Gaussian processes (DGPs) offer a more flexible alternative while still reaping the benefits of traditional GPs. I provide an implementation of DGP surrogates that prioritizes prediction accuracy and estimates of uncertainty. For computer simulations that are very costly to run, I provide a method of sequentially selecting input configurations to maximize learning from a fixed budget of simulator evaluations. I propose novel methods for selecting input configurations when the goal is to optimize the response or identify regions that correspond to system "failures". When abundant simulation evaluations are available, I provide an approximation which allows for faster DGP model fitting without compromising predictive power. I thoroughly vet my methods on both synthetic "toy" datasets and real aeronautic computer experiments.

No description available.

The training literature suggests that ongoing support (e.g., consultation) following initial training enhances training outcomes, yet little is known about the critical components of ongoing support and the lasting effects of ongoing support. The present study examined components of consultation calls that were provided to 99 community clinicians following training in the delivery of cognitive-behavioral therapy (CBT) for youth anxiety. The 104 recorded consultation calls were coded for content and consultative methods present. A subset of the training sample (N = 50) completed a 2-year follow-up interview during which they reported on their implementation rates of CBT since ending consultation. They also completed measures assessing CBT knowledge and attitudes toward evidence-based practices (EBPs). It was hypothesized that active learning (i.e., role-plays) would predict therapist adherence, skill, self-efficacy, and satisfaction at postconsultation, but regression analyses found no significant relation. However, level of clinician involvement during consultation calls significantly positively moderated the relation between active learning and clinician skill. Analyses of the follow-up data indicated (a) high implementation rates of CBT and (b) maintenance of overall attitudes toward EBPs, willingness to implement EBPs if mandated, views regarding the appeal of EBPs, and beliefs regarding the clinical utility of EBPs. A significant decline in CBT knowledge and openness toward EBPs was observed. Consultation call attendance positively predicted therapist CBT knowledge, overall attitudes toward EBPs, and attitudes regarding the appeal and clinical utility of EBPs at the 2-year follow-up. Implications, strengths and limitations, and future directions are discussed. / Psychology

The purpose of this study was to describe the implementation of contextual learning practices in a biology class. Research contends that contextual learning classrooms are active learning environments where students are involved in "hands-on" team projects and the teacher assumes a facilitator role. In this student-centered classroom, students take ownership and responsibility for their own learning. This study examined these assertions and other factors that emerged as the study developed. The research methods used were qualitative. The subject for this study was a biology teacher with twenty-six years of experience who implemented contextual learning practices in two of her biology classes in the 1997-98 school year. As the teacher confronted contextual learning, we engaged in collaborative research that included fourteen interviews transcribed verbatim for analysis, classroom observations and the teacher's written reports. Throughout the study, factors developed that adversely affected contextual learning practices. These factors were discipline, curriculum, and administrative decisions over which the teacher had no control. These are examined along with their consequences for implementing a contextual classroom. Successful practices that worked in the teacher's classroom were also determined and included the teacher's "failure is not an option" policy, mandatory tutoring, behavior contracts, high expectations and teamed projects. Besides contextual learning, a key component of the study was the collaborative research process and its meaning to the subject, the researcher and future researchers who attempt this collaborative approach. The study's conclusion indicate that scheduling, multiple repeaters, discipline and the state Standards of Learning moved the teacher away from contextual learning practices to a more teacher-directed classroom. Two recommendations of this study are that further research is needed to study how the state Standards of Learning have affected instructional practices and the effect of administrative decisions that influence the level of teacher success in the classroom. / Ed. D.