Proceedings of the Annual Meeting of the Cognitive Science Society

The ability of humans to quickly identify general conceptsfrom a handful of images has proven difficult to emulate withrobots. Recently, a computer architecture was developed thatallows robots to mimic some aspects of this human ability bymodeling concepts as cognitive programs using an instructionset of primitive cognitive functions. This allowed a robot toemulate human imagination by simulating candidate programsin a world model before generalizing to the physical world.However, this model used a naive search algorithm that re-quired 30 minutes to discover a single concept, and becameintractable for programs with more than 20 instructions. Tocircumvents this bottleneck, we present an algorithm that emu-lates the human cognitive heuristics of object factorization andsub-goaling, allowing human-level inference speed, improvingaccuracy, and making the output more explainable.