Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

1. Interaction. The interactions learners have with each other build interpersonal skills, such as listening, politely interrupting, expressing ideas, raising questions, disagreeing, paraphrasing, negotiating, and asking for help. 2. Interdependence. Learners must depend on one another to accomplish a common objective. Each group member has specific tasks to complete, and successful completion of each member’s tasks results in attaining the overall group objective.

将“Cooperative Learning”融入课堂——浅谈英语素质教育

/pdf/a-break-in-the-clouds-towards-a-cloud-definition-svovsw1r5a.pdf

A Break in the Clouds: Towards a Cloud Definition

Automated driving systems (ADSs) promise a safe, comfortable and efficient driving experience. However, fatalities involving vehicles equipped with ADSs are on the rise. The full potential of ADSs cannot be realized unless the robustness of state-of-the-art is improved further. This paper discusses unsolved problems and surveys the technical aspect of automated driving. Studies regarding present challenges, high-level system architectures, emerging methodologies and core functions including localization, mapping, perception, planning, and human machine interfaces, were thoroughly reviewed. Furthermore, many state-of-the-art algorithms were implemented and compared on our own platform in a real-world driving setting. The paper concludes with an overview of available datasets and tools for ADS development.

A Survey of Autonomous Driving: Common Practices and Emerging Technologies

Linked: The New Science of Networks

This paper investigates the modeling of the personal driving style of various vehicle drivers based on several driving parameters. The purpose of such an endeavor is to classify the drivers according to their risk-proneness within the larger context of increasing traffic safety, which is a major concern worldwide. This information is valuable especially for those involved in fleet management and it can be used to improve and to make safer the driving style of various individuals who serve within that fleet. Equally important, such information could help any driver to see the danger within his or her driving style. Cluster and principal component analyses from exploratory statistics have been used to identify and explain drivers grouping according to their driving behavior. The driving parameters (behavioral indices) are collected from urban traffic by an in-house developed GPS-based device and sent to a

/pdf/driving-style-analysis-using-data-mining-techniques-4o385s75hi.pdf

Driving Style Analysis Using Data Mining Techniques

New technological developments have made it possible to interact with computer systems and applications anywhere and anytime. It is vital that these applications are able to adapt to the user, as a person, and to its current situation, whatever that is. Therefore, the premises for evolution towards a learning society and a knowledge economy are present. Hence, there is a stringent demand for new learner-centred frameworks that allow active participation of learners in knowledge creation within communities, organizations, territories and society, at large. This paper presents the multi-agent architecture of our context-aware system and the learning scenarios within ubiquitous learning environments that the system provides support for. This architecture is the outcome of our endeavour to develop ePH, a system for sharing public interest information and knowledge, which is accessible through always-on, context-aware services.

/pdf/u-learning-within-a-context-aware-multiagent-environment-l8s2jg4oxs.pdf

U-Learning Within A Context-Aware Multiagent Environment

Advances in Grid Computing

Finding effectively open educational resources and open courseware that are the most relevant and that have the best quality for a specific user’s need, in a particular context, becomes more and more demanding. Hence, even though teachers and learners (enrolled students or self-learners as well) get to a greater extent support in finding the right educational resources, they still cannot rely on support for evaluating their quality and relevance, and, therefore, there is a stringent need for effective search and discovery tools that are able to locate high quality educational resources. We propose here a multi-agent system for evaluation and classification of open educational resources and open courseware (called MASECO) based on our socio-constructivist quality model. MASECO supports learners and instructors in their quest for the most appropriate educational resource that fulfills properly their educational needs in a given context. Faculty, educational institutions, developers, and quality assurance experts may also benefit from using it.

MASECO: A Multi-agent System for Evaluation and Classification of OERs and OCW Based on Quality Criteria

Education has been highly affected during the Covid pandemic. From one day to another, from kindergartens to universities, everyone involved in education has struggled to keep it going despite all the difficulties and restrictions. In our department, we coordinate two study programs in Computer Science (bachelor and master level). More than a year ago, we started to use the Discord communication platform to keep in touch in real time with our students and alumni. Our initial goal has been to create a strong ever growing community, in which our students, their former colleagues, and faculty can communicate easily. When the lockdown started, it was obvious that continuing to build and expand this community was the way to go. The last semester and the current one, we have been using Discord enhanced by a set of in-house developed scripts to communicate with the students, to keep going with both lectures and laboratories, according to the schedule, to have both the semester and the graduation exams, and so on. In this paper, we present our approach of continuing education during the pandemic (both requirements and solutions), and the lessons learnt during this experience.

/pdf/learning-during-covid-19-pandemic-online-education-community-z0hmrrz5sn.pdf

Zoran Constantinescu

Papers

Driving Style Analysis Using Data Mining Techniques

U-Learning Within A Context-Aware Multiagent Environment

Advances in Grid Computing

MASECO: A Multi-agent System for Evaluation and Classification of OERs and OCW Based on Quality Criteria

Learning During COVID-19 Pandemic: Online Education Community, Based on Discord