Efficient Monte Carlo methods for multi-dimensional learning with classifier chains

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance – at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest-performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.

The usefulness of Usability and User Experience evaluation methods on an e-Learning platform development from a developer's perspective: A case study

The development of a web platform is a complex and interdisciplinary task, where people with different roles such as project manager, designer or developer participate. Different usability and User Experience evaluation methods can be used in each stage of the development life cycle, but not all of them have the same influence in the software development and in the final product or system. This article presents the study of the impact of these methods applied in the context of an e-Learning platform development. The results show that the impact has been strong from a developer's perspective. Developer team members considered that usability and User Experience evaluation allowed them mainly to identify design mistakes, improve the platform's usability and understand the end users and their needs in a better way. Interviews with potential users, clickmaps and scrollmaps were rated as the most useful methods. Finally, these methods were considered unanimously very useful in the context of the entire software development, only comparable to SCRUM meetings and overcoming the rest of involved factors.

Investigating and Understanding Student Learning Outcomes in an Online and Face-to-Face Graduate Level Legal Administration Course: An Embedded Mixed Methods Design

Online education is a new teaching and learning medium with few current guidelines for faculty, administrators or students. Its rapid growth over the last decade has challenged academic institutions to keep up with the demand, while also providing a quality education. Our understanding of the factors that determine quality and effective online learning experiences that lead to student learning outcomes is still evolving. There is a lack of consensus on the effectiveness of online versus face-to-face education in the current research. The U.S. Department of Education conducted a meta-analysis in 2009 and concluded that student-learning outcomes in online courses were equal to and, often times, better than face-to-face traditional courses. Subsequent research has found contradictory findings, and further inquiry is necessary. The purpose of this embedded mixed methods design research study is to further our understanding of the factors that create quality and successful educational outcomes in an online course. To achieve this, the first phase of this study measured and compared learning outcomes in an online and in class graduate-level legal administration course. The second phase of the study entailed interviews with those students in both the online and face-to-face sections to understand their perspectives on the factors contributing to learning outcomes. Six themes emerged from the qualitative findings: convenience, higher order thinking, discussions, professor engagement, professor and student interaction, and face-to-face interaction. Findings from this study indicate the factors students perceive as contributing to learning outcomes in an online course are consistent among all students and are supported in the existing literature. Higher order thinking, however, emerged as a stronger theme than indicated in the current research, and the face-to-face nature of the traditional classroom may be more an issue of familiarity than a factor contributing to learning outcomes. As education continues to reach new heights and developments in technology advance, the factors found to contribute to student learning outcomes will be refined and enhanced. These developments will continue to transform the ways in which we deliver and receive knowledge in both traditional and online classrooms. While there is a growing body of research on online education, the field’s evolution has unsettled earlier findings and posed new areas to investigate.

What We Are Learning About the Diverse Backgrounds of Academic Library Users: An Overview of Research Designs and Methods in Information Behaviour Studies

Academic libraries increasingly serve a more diverse population of users not only in regard to race and ethnicity, but also to age, gender, language, sexual orientation, and national and cultural backgrounds. This papers reports the findings of the study that explored information behaviour research as a potential source of information about diversity of academic library users and examined the relationship between the use of different research designs and data collection methods and the information gathered about users’ diverse backgrounds. The study found that information behaviour research offers limited insight into the diversity of academic library users. The choice of a research design was not critical but the use of multiple data collection played a role in gathering information about culturally diverse users.

Learning and generalization of structural descriptions : evaluation criteria and comparative review of selected methods /

"February 1980."

Vocabulary learning through use of the picture-word inductive model for young English learners in China: A mixed methods examination using Cognitive Load Theory

English has been taught as a core and compulsory subject in China for decades. Recently, the demand for English in China has increased dramatically. China now has the world's largest English-learning population. The traditional English-teaching method cannot continue to be the only approach because it merely focuses on reading, grammar and translation, which cannot meet English learners and users' needs (i.e., communicative competence and skills in speaking and writing). ^ This study was conducted to investigate if the Picture-Word Inductive Model (PWIM), a new pedagogical method using pictures and inductive thinking, would benefit English learners in China in terms of potential higher output in speaking and writing. With the gauge of Cognitive Load Theory (CLT), specifically, its redundancy effect, I investigated whether processing words and a picture concurrently would present a cognitive overload for English learners in China. ^ I conducted a mixed methods research study. A quasi-experiment (pretest, intervention for seven weeks, and posttest) was conducted using 234 students in four groups in Lianyungang, China (58 fourth graders and 57 seventh graders as an experimental group with PWIM and 59 fourth graders and 60 seventh graders as a control group with the traditional method). No significant difference in the effects of PWIM was found on vocabulary acquisition based on grade levels. Observations, questionnaires with open-ended questions, and interviews were deployed to answer the three remaining research questions. A few students felt cognitively overloaded when they encountered too many writing samples, too many new words at one time, repeated words, mismatches between words and pictures, and so on. Many students listed and exemplified numerous strengths of PWIM, but a few mentioned weaknesses of PWIM. The students expressed the idea that PWIM had a positive effect on their English teaching. ^ As integrated inferences, qualitative findings were used to explain the quantitative results that there were no significant differences of the effects of the PWIM between the experimental and control groups in both grade levels, from four contextual aspects: time constraints on PWIM implementation, teachers' resistance, how to use PWIM and PWIM implemented in a classroom over 55 students.^

Vocabulary Learning through Use of the Picture-Word Inductive Model for Young English Learners in China: A Mixed Methods Examination Using Cognitive Load Theory

English has been taught as a core and compulsory subject in China for decades. Recently, the demand for English in China has increased dramatically. China now has the world’s largest English-learning population. The traditional English-teaching method cannot continue to be the only approach because it merely focuses on reading, grammar and translation, which cannot meet English learners and users’ needs (i.e., communicative competence and skills in speaking and writing). This study was conducted to investigate if the Picture-Word Inductive Model (PWIM), a new pedagogical method using pictures and inductive thinking, would benefit English learners in China in terms of potential higher output in speaking and writing. With the gauge of Cognitive Load Theory (CLT), specifically, its redundancy effect, I investigated whether processing words and a picture concurrently would present a cognitive overload for English learners in China. I conducted a mixed methods research study. A quasi-experiment (pretest, intervention for seven weeks, and posttest) was conducted using 234 students in four groups in Lianyungang, China (58 fourth graders and 57 seventh graders as an experimental group with PWIM and 59 fourth graders and 60 seventh graders as a control group with the traditional method). No significant difference in the effects of PWIM was found on vocabulary acquisition based on grade levels. Observations, questionnaires with open-ended questions, and interviews were deployed to answer the three remaining research questions. A few students felt cognitively overloaded when they encountered too many writing samples, too many new words at one time, repeated words, mismatches between words and pictures, and so on. Many students listed and exemplified numerous strengths of PWIM, but a few mentioned weaknesses of PWIM. The students expressed the idea that PWIM had a positive effect on their English teaching. As integrated inferences, qualitative findings were used to explain the quantitative results that there were no significant differences of the effects of the PWIM between the experimental and control groups in both grade levels, from four contextual aspects: time constraints on PWIM implementation, teachers’ resistance, how to use PWIM and PWIM implemented in a classroom over 55 students.

Metal measurement in aquatic environments by passive sampling methods: Lessons learning from an in situ intercomparison exercise

Passive sampling devices (PS) are widely used for pollutant monitoring in water, but estimation of measurement uncertainties by PS has seldom been undertaken. The aim of this work was to identify key parameters governing PS measurements of metals and their dispersion. We report the results of an in situ intercomparison exercise on diffusive gradient in thin films (DGT) in surface waters. Interlaboratory uncertainties of time-weighted average (TWA) concentrations were satisfactory (from 28% to 112%) given the number of participating laboratories (10) and ultra-trace metal concentrations involved. Data dispersion of TWA concentrations was mainly explained by uncertainties generated during DGT handling and analytical procedure steps. We highlight that DGT handling is critical for metals such as Cd, Cr and Zn, implying that DGT assembly/dismantling should be performed in very clean conditions. Using a unique dataset, we demonstrated that DGT markedly lowered the LOQ in comparison to spot sampling and stressed the need for accurate data calculation.

Robotic Sensing and Manipulation of Deformable Linear Objects with Learning-based methods

Nowadays robotic applications are widespread and most of the manipulation tasks are efficiently solved. However, Deformable-Objects (DOs) still represent a huge limitation for robots. The main difficulty in DOs manipulation is dealing with the shape and dynamics uncertainties, which prevents the use of model-based approaches (since they are excessively computationally complex) and makes sensory data difficult to interpret. This thesis reports the research activities aimed to address some applications in robotic manipulation and sensing of Deformable-Linear-Objects (DLOs), with particular focus to electric wires. In all the works, a significant effort was made in the study of an effective strategy for analyzing sensory signals with various machine learning algorithms. In the former part of the document, the main focus concerns the wire terminals, i.e. detection, grasping, and insertion. First, a pipeline that integrates vision and tactile sensing is developed, then further improvements are proposed for each module. A novel procedure is proposed to gather and label massive amounts of training images for object detection with minimal human intervention. Together with this strategy, we extend a generic object detector based on Convolutional-Neural-Networks for orientation prediction. The insertion task is also extended by developing a closed-loop control capable to guide the insertion of a longer and curved segment of wire through a hole, where the contact forces are estimated by means of a Recurrent-Neural-Network. In the latter part of the thesis, the interest shifts to the DLO shape. Robotic reshaping of a DLO is addressed by means of a sequence of pick-and-place primitives, while a decision making process driven by visual data learns the optimal grasping locations exploiting Deep Q-learning and finds the best releasing point. The success of the solution leverages on a reliable interpretation of the DLO shape. For this reason, further developments are made on the visual segmentation.

Comparison of Explicit and Implicit Methods of Cross-Cultural Learning in an International Classroom

The paper addresses a gap in the literature concerning the difference between enhanced and not enhanced cross-cultural learning in an international classroom. The objective of the described research was to clarify if the environment of international classrooms could enhance cross-cultural competences significantly enough or if additional focus on cross-cultural learning as an explicit objective of learning activities would add substantially to the experience. The research question was defined as “how can a specific exercise focused on cross-cultural learning enhance the cross-cultural skills of university students in an international classroom?”. Surveys were conducted among interna- tional students in three leading Central-European Universities in Lithuania, Poland and Hungary to measure the increase of their cross-cultural competences. The Lithuanian and Polish classes were composed of international students and concentrated on International Management/Business topics (explicit method). The Hungarian survey was done in a general business class that just happened to be international in its composition (implicit method). Overall, our findings prove that the implicit method resulted in comparable, somewhat even stronger effectiveness than the explicit method. The study method included the analyses of students’ individual increases in each study dimension and construction of a compound measure to note the overall results. Our findings confirm the power of the international classroom as a stimulating environment for latent cross-cultural learning even without specific exercises focused on cross-cultural learning itself. However, the specific exercise did induce additional learning, especially related to cross-cultural awareness and communication with representatives of other cultures, even though the extent of that learning may be interpreted as underwhelming. The main conclusion from the study is that the diversity of the students engaged in a project provided an environment that supported cross-cultural learning, even without specific culture-focused reflections or exercises.

Development of advanced methods for the simulation of the reacting mixture formation in internal combustion engines with the use of machine learning algorithms

Besides increasing the share of electric and hybrid vehicles, in order to comply with more stringent environmental protection limitations, in the mid-term the auto industry must improve the efficiency of the internal combustion engine and the well to wheel efficiency of the employed fuel. To achieve this target, a deeper knowledge of the phenomena that influence the mixture formation and the chemical reactions involving new synthetic fuel components is mandatory, but complex and time intensive to perform purely by experimentation. Therefore, numerical simulations play an important role in this development process, but their use can be effective only if they can be considered accurate enough to capture these variations. The most relevant models necessary for the simulation of the reacting mixture formation and successive chemical reactions have been investigated in the present work, with a critical approach, in order to provide instruments to define the most suitable approaches also in the industrial context, which is limited by time constraints and budget evaluations. To overcome these limitations, new methodologies have been developed to conjugate detailed and simplified modelling techniques for the phenomena involving chemical reactions and mixture formation in non-traditional conditions (e.g. water injection, biofuels etc.). Thanks to the large use of machine learning and deep learning algorithms, several applications have been revised or implemented, with the target of reducing the computing time of some traditional tasks by orders of magnitude. Finally, a complete workflow leveraging these new models has been defined and used for evaluating the effects of different surrogate formulations of the same experimental fuel on a proof-of-concept GDI engine model.

Methods for integrating machine learning and constrained optimization

In the framework of industrial problems, the application of Constrained Optimization is known to have overall very good modeling capability and performance and stands as one of the most powerful, explored, and exploited tool to address prescriptive tasks. The number of applications is huge, ranging from logistics to transportation, packing, production, telecommunication, scheduling, and much more. The main reason behind this success is to be found in the remarkable effort put in the last decades by the OR community to develop realistic models and devise exact or approximate methods to solve the largest variety of constrained or combinatorial optimization problems, together with the spread of computational power and easily accessible OR software and resources. On the other hand, the technological advancements lead to a data wealth never seen before and increasingly push towards methods able to extract useful knowledge from them; among the data-driven methods, Machine Learning techniques appear to be one of the most promising, thanks to its successes in domains like Image Recognition, Natural Language Processes and playing games, but also the amount of research involved. The purpose of the present research is to study how Machine Learning and Constrained Optimization can be used together to achieve systems able to leverage the strengths of both methods: this would open the way to exploiting decades of research on resolution techniques for COPs and constructing models able to adapt and learn from available data. In the first part of this work, we survey the existing techniques and classify them according to the type, method, or scope of the integration; subsequently, we introduce a novel and general algorithm devised to inject knowledge into learning models through constraints, Moving Target. In the last part of the thesis, two applications stemming from real-world projects and done in collaboration with Optit will be presented.

Concepts and methods for efficient decentralized learning in federated settings

Deep Neural Networks (DNNs) have revolutionized a wide range of applications beyond traditional machine learning and artificial intelligence fields, e.g., computer vision, healthcare, natural language processing and others. At the same time, edge devices have become central in our society, generating an unprecedented amount of data which could be used to train data-hungry models such as DNNs. However, the potentially sensitive or confidential nature of gathered data poses privacy concerns when storing and processing them in centralized locations. To this purpose, decentralized learning decouples model training from the need of directly accessing raw data, by alternating on-device training and periodic communications. The ability of distilling knowledge from decentralized data, however, comes at the cost of facing more challenging learning settings, such as coping with heterogeneous hardware and network connectivity, statistical diversity of data, and ensuring verifiable privacy guarantees. This Thesis proposes an extensive overview of decentralized learning literature, including a novel taxonomy and a detailed description of the most relevant system-level contributions in the related literature for privacy, communication efficiency, data and system heterogeneity, and poisoning defense. Next, this Thesis presents the design of an original solution to tackle communication efficiency and system heterogeneity, and empirically evaluates it on federated settings. For communication efficiency, an original method, specifically designed for Convolutional Neural Networks, is also described and evaluated against the state-of-the-art. Furthermore, this Thesis provides an in-depth review of recently proposed methods to tackle the performance degradation introduced by data heterogeneity, followed by empirical evaluations on challenging data distributions, highlighting strengths and possible weaknesses of the considered solutions. Finally, this Thesis presents a novel perspective on the usage of Knowledge Distillation as a mean for optimizing decentralized learning systems in settings characterized by data heterogeneity or system heterogeneity. Our vision on relevant future research directions close the manuscript.