Pilot: Using Causal Relations to Guide Multi-Level Creative Processes

James Reggia reggia@cs.umd.edu(Principal Investigator)

University of Maryland College Park
COLLEGE PARK, MD 20742 301/405-6269


While evolutionary computing to support creativity appears very promising, current methods include human creativity to directly guide the search process and to replace the fitness function so the creativity is not part of the computational process. This project considers causal relations and cause and effect reasoning as important aspects of human creativity in problem solving, scientific discovery, invention and design. The primary goal of this research is to develop and evaluate methods for causally guided evolutionary creativity by incorporating cause and effect relationships as part of the fitness function. This project will develop an understanding of the fundamental principles involved in integrating causal inference with the genetic search process that has been used successfully in past creative evolutionary systems. Undergraduate students will be encouraged to integrate their own projects within the proposed creative evolutionary research. Other broader impacts are that the causal relations encoded for the specific creativity test cases should be of value to creativity researchers in general, and the resultant designs of case studies of oscillatory memories and antenna arrays will be of interest to individuals in cognitive neuroscience and electrical engineering.