“…Compared to the best object recognition systems, people learn richer concepts from fewer examples. Recent research in cognitive science, machine learning, and computer vision has begun to model learning as a form of program induction (Zhu & Mumford, 2006;Savova & Tenenbaum, 2008;Savova et al, 2009;Stuhlmuller et al, 2010;Piantadosi, 2011;Piantadosi et al, 2012;Khemlani et al, 2013;Goodman et al, 2015;Lake et al, 2015;Ellis et al, 2015;Yildirim & Jacobs, 2015;Rothe et al, 2017;Amalric et al, 2017;Ellis et al, 2018;Depeweg et al, 2018), yet there are steep computational obstacles to building a general purpose program learner. It is unclear how the mind could learn genuine programs in a general way.…”