Educational Technologies

Educational Technologies Overview

In the DEMO Lab at Brandeis University's Computer Science Department, we have directed a number of our research projects towards educational technologies. We synthesize several components of our work, uniting a unique combination of technologies and theories from which we are building the educational environment. We start with our experience in machine learning, where we have co-evolved software agents to play games. We add to this our success using the Internet to facilitate a new form of co-evolution between humans and software agents. Finally, we carry these concepts into the educational arena.

Based in Theory: For the past 8 years, the DEMO lab has focused on the process of "self-organization," how complex systems can, with enough time and energy, create themselves. We approach problems in this field using reductionist techniques, seeking the core principles of discovery that appear to be at the basis of biological development and evolution. Historically, machine learning has taken its lead from examining theories in human learning. Our research work attempts to complete the circle, applying knowledge gained from studying machine learning to bear in the human learning arena. Mission and Goals

Spellbee

Our research explores the learning science at the juncture of evolution and game theory and the technology for on-line communities. We have developed and are currently testing a proof of concept of our research questions. Our focus is basic science, evaluating approaches for the automatic management of peer matching and motivation in learning communities. We will be implementing computational methods for matching learners together and perform experiments motivating peers to create appropriate challenges to each other. Our system is being implemented as a framework where central issues in educational multiplayer learning groups can be tested empirically. We will continue to develop our web delivery system. Usability and workflow will be addressed, from the varying perspectives of students, educators, and evaluators. We are currently actively testing this project, please visit us.

Theory Modeling

Our pedagogical hypothesis is that students learn best when they are continually challenged and have many opportunities for getting learning rewards. This requires an environment with diverse affordances for learning. We will conduct a focused set of experiments based on our "Teacher's Dilemma" game to discover if we can find the structures and parameters which maximize appropriate challenge in a multiplayer one-to-one learning environment. If we find these parameters, we believe it will be a significant breakthrough in educational science. By implementing these mechanisms on the Internet, our goal is to create an adaptive system that encourages students to be coaches for each other, leading to tremendous efficiency, in terms of the number of adults necessary per child. We will test our theoretic framework on peers of mixed age and diverse geographic regions, using relatively simple matching algorithms to bring like-graded students together for repeated learning opportunities.

[email protected]