Active Transfer Learning for Latent Competencies Navy STTR FY2015.A Sol No.: Navy STTR FY2015.A Topic No.: N15A-T013 Topic Title: Active Transfer Learning for Latent Competencies Proposal No.: N15A-013-0141 Firm: Eduworks Corporation 136 SW Washington Ste 203 Corvallis, Oregon 97333-4875 Contact: Robby Robson Phone: (541) 753-0844 Web Site: www.eduworks.com Abstract: Training systems and programs can be made more efficient and effective by understanding how knowledge of one domain affects a learner's ability to acquire skills in another. This Phase I STTR will result in a novel method for modeling this transfer process and predicting when transfer takes place. Underlying this method is a machine learning algorithm that actively solicits input from Subject Matter Experts (SMEs) to learn the latent competencies that influence the ability of learners to transfer knowledge across subjects. The outputs of the algorithm include domain models that can be used in a variety of intelligent tutoring systems (ITS) and algorithms that combine general models with individual views to optimize predictions. The inputs consist of assessments or evaluations of previous learners. Once the machine learning algorithms have learned the structure of one domain, they can more efficiently learn the structure of other domains. In Phase I we will implement the underlying algorithms and create a proof-of-concept software demo that enables SMEs to interact with them. The demo will processes data from two domains and produce results that an ITS will use to adjust how it presents content in the second domain based on learner outcomes in the first. Benefits: This research will ultimately result in an intelligent, cloud-based platform that can be used to improve the efficiency and efficacy of training systems and training programs. The algorithms and software we develop will be used to provide targeted learning opportunities, to optimize individual training trajectories, to evaluate potential career training, and to better identify likely candidates for training in in-demand specialties. These capabilities will enable military and corporate training organizations to "do more with less" and, in workforce development settings, will help veterans and other jobseekers evaluate career paths against the training required based on their individual history. Finally, the proposed research will develop a method that can be applied to other situations where the goal is to predict performance on a complex task based on past performance and it is possible to enlist the aid of SMEs or to otherwise "crowd source" information needed for machine learning algorithms to identify hidden factors. Return