We propose an intelligent assessment concept that will discover and reason about KSAs in multiple instruc-tional domains and settings. SoarTech will team with world-class researchers from the University of Califor-nia, Davis and the University of Memphis to research and develop TARGET: Transfer via Active Requests to Generalize Effective Training. TARGET will enhance SoarTechs assessment system DARTS, currently in schoolhouse use, with Active Transfer Learning that models student performance and skills in multiple in-structional domains, identifies underlying skills, finds relationships between domains, and actively queries human experts to continually improve its model. Learning Space Theory makes detailed cross-domain models tractable, enables inference that is understandable to nontechnical users and mathematically sound, and di-rects adaptive testing or intelligent tutoring. With these components, TARGET can predict what KSAs might be important to train a new capability, reduce testing needed to estimate students underlying proficiency, and remain accessible to instructors and SMEs who will be able to understand, trust, control, and update the sys-tem
Benefit: TARGET will improve personnel recruitment, selection, accession, retention and professional development because it will increase the precision, accuracy, and amount of information available about individual skill proficiencies. TARGET will both increase training effectiveness and also reduce required time and costs by eliminating duplicative training that merely focuses on superficial test scores or checklists rather than actual, underlying proficiency. Finally, TARGET will enable training to be tailored to the individual and team any-where, anytime by offering a detailed and up-to-date understanding of individual and team competencies that evolves to track the changing nature of military operations.
Keywords: Active Transfer Learning, Active Transfer Learning, Knowledge Spaces, Intelligent Tutoring, Training, Learning Spaces, Crowd sourcing