Shane Eric Celis

Papers

Total Citations

H-Index

About

Shane Eric Celis is a researcher whose work bridges human intuition and computational optimization, with a focus on interactive evolutionary algorithms (IEAs) and robotics. His most-cited paper, "Avoiding local optima with user demonstrations and low-level control" (2013, 11 citations), introduces a novel approach where users directly demonstrate preferred behaviors rather than simply ranking individuals—a method that helps algorithms escape local optima more effectively. This contribution refines how human feedback can guide complex search processes, particularly in low-level control tasks. Celis’s research emphasizes the synergy between user input and machine learning, offering practical solutions for domains like robotics and design. While his citation count reflects a focused, early-stage impact, his work stands out for its innovative integration of demonstration-based interaction, a concept that has influenced subsequent studies in human-in-the-loop optimization. For students and researchers exploring interactive AI, Celis’s approach offers a compelling example of how direct human guidance can enhance algorithmic performance, making his contributions a valuable reference for those seeking to blend user expertise with computational search.