Predicting suspended sediment load in water resource management requires efficient and reliable predicted models. This study considers the support vector regression method to predict daily suspended sediment load. Since the SVR has unknown parameters, the observer-teacher-learner-based Optimization method is integrated with the SVR model to provide a novel hybrid predictive model. The SVR combined with the genetic algorithm is used as an alternative model. To explore the performance and application of the proposed models, five input combinations of rainfall and discharge (...) data of Cham Siah River catchment are provided. The predictive models are assessed using various numerical and visual indicators. The results indicate that the SVR-OTLBO model offers a higher prediction performance than other models employed in the current study. Specifically, SVR-OTLBO model offers highest Pearson correlation coefficient, Willmott’s Index, ratio of performance to IQ, and modified index of agreement and the lowest relative root mean square error in comparison with SVR-GA and SVR models, respectively. (shrink)

The bias–variance tradeoff is a theoretical concept that suggests machine learning algorithms are susceptible to two kinds of error, with some algorithms tending to suffer from one more than the other. In this letter, we claim that the bias–variance tradeoff is a general concept that can be applied to human cognition as well, and we discuss implications for research in cognitive science. In particular, we show how various strands of research in cognitive science can be interpreted in light of the (...) bias–variance tradeoff, giving insight into individual differences in learning, the nature of cognitive processes, and debates in cognitive science research. (shrink)

An important part of research is situating one’s work in a body of existing literature, thereby connecting to existing ideas. Despite this, the various kinds of relationships that might exist among academic literature do not appear to have been formally studied. Here I present a graphical representation of academic work in terms of entities and relations, drawing on structure-mapping theory (used in the study of analogies). I then use this representation to present a typology of operations that could relate two (...) pieces of academic work. I illustrate the various types of relationships with examples from medicine, physics, psychology, history and philosophy of science, machine learning, education, and neuroscience. The resulting typology not only gives insights into the relationships that might exist between static publications, but also the rich process whereby an ongoing research project evolves through interactions with the research literature. (shrink)

This workshop unearths the potential of applying principles of cybernetics to curriculum and educational technology design. Here, we focus on using technology-assisted learning scenarios at the confluence of education, psychology, and computer science as an asset for adults to learn the skills for critical Internet navigation; skills we argue are an integral part of life in the Information Age. The first part of the workshop begins with an introduction to what von Foerster called Gordon Pask’s first theorem (a basic framework (...) of human-tool conversations), which was used to design classes in heuristics at the University of Illinois, Urbana, and involved project-based community and artefact development. It then describes how this approach was replicated to co-design educational psychology classes at The Ohio State University in 2022-2023 to help preservice teachers engage in metareflection about their future careers. A small group discussion between workshop participants follows to understand how tools and activities used in these classes (social media, block programming, co-authoring, podcasting) can be adapted for other subject classrooms. The second part of the workshop focuses on fine-tuning the build of educational technologies like search engines to spur concept development. -/- We invite volunteers to interact with our Paskian search engine, ThoughtShuffler, which uses an uncertainty regulation mechanism to organize search results for lateral reading, and present results from an experimental study showing the tool has the potential to engender higher-order reflectivity in information search. We suggest principles of cybernetics can be used to co-design sociotechnical systems and sharpen both human and machine functioning within them, presenting hopes for human adaptation to an information-saturated future. (shrink)