Adaptive Design of Experiments Based on Gaussian Processes
We consider a problem of adaptive design of experiments for Gaussian process regression. We introduce a Bayesian framework, which provides theoretical justification for some well-know heuristic criteria from the literature and also gives an opportunity to derive some new criteria. We also perform testing of methods in question on a big set of multidimensional functions.
Computer simulation, an active learning technique, is now one of the advanced pedagogical technologies. The use of simulation games in the educational process allows students to gain a firsthand understanding of the processes of real life. Public administration, public policy, and political science courses increasingly adopt simulation games in universities worldwide. Besides person-to-person simulation games, there are computer-based simulations in public administration education. Currently in Russia the use of computer-based simulation games in Master of Public Administration (MPA) curricula is quite limited. This paper focuses on computer-based simulation games for students of MPA programs. Our aim was to analyze outcomes of implementing such games in MPA curricula. We have done so by (1) developing three computer- based simulation games about allocating public finances, (2) testing the games in the learning process, and (3) conducting a posttest examination to evaluate the effect of simulation games on students’ knowledge of municipal finances. This study was conducted in the National Research University Higher School of Economics (HSE) and in the Russian Presidential Academy of National Economy and Public Administration (RANEPA) during the period September to December 2015, in Saint Petersburg, Russia. Two groups of students were randomly selected in each university and then randomly allocated either to the experimental or the control group. In control groups (n=12 in HSE, n=13 in RANEPA) students had traditional lectures. In experimental groups (n=12 in HSE, n=13 in RANEPA) students played three simulation games apart from traditional lectures. This exploratory research shows that the use of computer-based simulation games in MPA curricula can improve students’ outcomes by 38%. In general, the experimental groups had better performance on the posttest examination (figure 2). Students in the HSE experimental group had 27.5% better scores than students in the HSE control group. Students of the RANEPA experimental group had 38.0% better scores than students in the RANEPA control group. Research indicates that lecture-based courses are less effective than courses with more interactive approaches. Therefore, our study highlights the need to implement computer-based simulation games in MPA programs in Russian universities. Computer-based simulation games provide students with practical skills for their future careers.
Humans can adapt their behavior by learning from the consequences of their own actions or by observing others. Gradual active learning of action-outcome contingencies is accompanied by a shift from feedback- to response-based performance monitoring. This shift is reflected by complementary learning-related changes of two ACC-driven ERP components, the feedback-related negativity (FRN) and the error-related negativity (ERN), which have both been suggested to signal events "worse than expected," that is, a negative prediction error. Although recent research has identified comparable components for observed behavior and outcomes (observational ERN and FRN), it is as yet unknown, whether these components are similarly modulated by prediction errors and thus also reflect behavioral adaptation. In this study, two groups of 15 participants learned action-outcome contingencies either actively or by observation. In active learners, FRN amplitude for negative feedback decreased and ERN amplitude in response to erroneous actions increased with learning, whereas observational ERN and FRN in observational learners did not exhibit learning-related changes. Learning performance, assessed in test trials without feedback, was comparable between groups, as was the ERN following actively performed errors during test trials. In summary, the results show that action-outcome associations can be learned similarly well actively and by observation. The mechanisms involved appear to differ, with the FRN in active learning reflecting the integration of information about own actions and the accompanying outcomes.
The article considers the conditions necessary for arranging educational environment, which can provide the required level of training. One of the key factors affecting the quality of education is the professional level of teachers, their ability and willingness to design their own trainingtechnologies and use non-standard methods of solving educational problems such as active learning. The article provides research on the assessment process of writing papers and project learning experiment.