Toward a Computational Model of Transfer

126 AI MAGAZINE The Defense Advanced Research Projects Agency (DARPA) Transfer Learning Program (TLP) explored the application of “transfer”—a notion well studied in psychology—to machine learning, where it was still novel. The aims of TLP were to understand and formally frame how this intuitively compelling psychological idea might apply in the computational context, build computational models of transfer learning (TL), and explore how these models might apply to practical learning tasks. TLP and the field as a whole made great strides in each of these dimensions. Indeed, the program has helped TL become a recognized subdiscipline of machine learning. Other articles in this special issue detail the work accomplished in TLP; this article focuses on a broad framing of the research conducted and an assessment of its progress, limitations, and challenges, from an admittedly personal but DARPA-influenced perspective.