We investigate the possibility to apply a known machine learning algorithm of Q-learning in the domain of a Virtual Learning Environment (VLE). It is important in this problem domain to have algorithms that learn their optimal values in a rather short time expressed in terms of the iteration number. The problem domain is a VLE in which an agent plays a role of the teacher. With time it moves to different states and makes decisions which regarding action to choose for moving from current state to the next state. Some actions taken are more efficient than others. The transition process through the set of states ends in a final (goal) state, one which provides the agent with the largest benefit possible. The best course of action is to reach the goal state with the maximum return available. This paper introduces a way of definition of a rewards matrix, which allows the maximum tolerance for the changes of a discounted reward value to be achieved. It also proposes way of an application of the Q-learning that allows a teaching policy to exist, which maps the situation in the learning environment.
This paper describes a didactical Computer Aided Software Engineering (CASE)-tool that was developed for use within the context of a course in object-oriented domain modelling. In particular, the tool was designed to address several inconveniences that challenge the realisation of the course objectives: the number of students enrolled does not allow for individual feedback (a); students have little opportunity to build a concrete information system, therefore they fail to predict the consequences of the different choices when building a conceptual model (b); students lack examples and practice on how to convert a conceptual model into a concrete information system (c); at the beginning of the course students have very different levels of prior knowledge leading to major differences in motivation and learning outcomes (d).
The tool was evaluated positively by the students and was shown to have a positive impact on the student's capabilities to construct object-oriented models.
It is argued that even better learning results can be realised by capitalizing on the opportunities for social interaction in an educational context.
Reflective practice is considered to play an important role in students' learning as they encounter difficult material. However, students in this situation sometimes do not behave reflectively, but in less productive and more problematic ways. This paper investigates how educators can recognize and analyze students' confusion, and determine whether students are responding reflectively or defensively. Qualitative data for the investigation comes from an upper-level undergraduate software engineering and design course that students invariably find quite challenging. A phenomenological analysis of the data, based on Heidegger's dynamic of rupture, provides useful insight to students' experience. A comparison between that approach and a sampling of classic sources in scholarship on learning, reflectiveness, and defensiveness has implications for teaching and education research in software design - and more generally. In addition, a clearer understanding of the concepts presented in this paper should enable faculty to bring a more sophisticated analysis to student feedback, and lead to a more informed and productive interpretation by both instructor and administration.
Although there are many high-quality models for program and evaluation planning, these models are often too intensive to be used in situations when time and resources are scarce. Additionally, there is little added value in using an elaborate and expensive program and evaluation planning procedure when programs are small or are planned to be short-lived. To meet the need for simplified models for program and evaluation planning, we describe a model that includes only what we consider to be the most essential outcomes-based program and evaluation planning steps: (a) how to create a logic model that shows how the program is causally expected to lead to outcomes, (b) how to use the logic model to identify the goals and objectives that the program is responsible for; (c) how to formulate measures, baselines, and targets from the goals and objectives; and (d) how to construct program activities that align with program targets.
A high quality review of the distance learning literature from 1992-1999 concluded that most of the research on distance learning had serious methodological flaws. This paper presents the results of a small-scale replication of that review. A sample of 66 articles was drawn from three leading distance education journals. Those articles were categorized by study type, and the experimental or quasi-experimental articles were analyzed in terms of their research methodologies. The results indicated that the sample of post-1999 articles had the same methodological flaws as the sample of pre-1999 articles: most participants were not randomly selected, extraneous variables and reactive effects were not controlled for, and the validity and reliability of measures were not reported.
In recent years a small number of web-based tools have been proposed to help students learn to write SQL query statements and also to assess students' SQL writing skills. SQLify is a new SQL teaching and assessment tool that extends the current state-of-the-art by incorporating peer review and enhanced automatic assessment based on database theory to produce more comprehensive feedback to students. SQLify (pronounced as squalify) is intended to yield a richer learning experience for students and reduce marking load for instructors. In this paper SQLify is compared with existing tools and important new features are demonstrated.
Motivating students of the Nintendo generation for Computer Science can only be achieved by providing them with an exiting and fresh CS1 course. The article describes the experience of redesigning the introductory programming course at ETH Zurich and shows how the combination of state-of-the-art visualizations with open project assignments enlivens students' enthusiasm for programming. It shows the setup and the involved libraries, provides example applications that were built in the course, and presents the data gathered in the evaluation of the open assignment.
This paper presents an approach for educators to evaluate student progress throughout a course, and not merely based on a final exam. We introduce progress reports and describe how these can be used as a tool to evaluate student learning and understanding during programming courses. Complemented with data from surveys and the exam, the progress reports can be used to build an overall picture of individual student progress in a course, and to answer questions related to how students (1) understand program code as a whole, (2) understand individual constructs, and (3) perceive the difficulty level of different programming topics. We also present results from using this approach in introductory programming courses at secondary level. Our initial experience from using the progress reports is positive, as they provide valuable information during the course, which most likely would remain uncovered otherwise.
The aim of the paper is to present the characteristics of certain dynamic programming strategies on the decision tree hidden behind the optimizing problems and thus to offer such a clear tool for their study and classification which can help in the comprehension of the essence of this programming technique.
The increasing number of children who need special education in Finland also requires an increasing amount of resources from teachers and a restructuring of the education system. Technology can be a part of the solution to this resource problem; however, for the technological solution to work, technologies need to be designed and implemented in new ways. Technologies used in special education in Finland can roughly be divided into four main categories; assistive technologies, communication technologies, and learning software. Last and the newest category concretizing technologies, such as educational robotics, have successfully been used in the Technologies for Children with Individual Needs Project. Possibilities provided by educational robotics have been extensive, not only because of the technology itself, but also because of how the technology has been implemented in innovative projects with school students. From this point of view, students with individual educational needs as well as those involved in inclusive education and harmonized school days could benefit from the use of technology.