Concept learning as motor program induction: A large-scale empirical study

26 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

From Red Wine to Red Tomato: Composition with Context (2017, unknown): “Compositionality has also been a key building block for systems used for visual question answering [4, 5], handwritten digits [32, 33], zero-shot detection [31], segmentation and pose estimation [59, 62].”
Discovering linguistic structures in speech: models and applications (2014, background): “The authors of [104] propose a hierarchical Bayesian model for one-shot classification, and one-shot generation of handwritten characters in the Omniglot corpus [103, 164].”
The Omniglot Challenge: A 3-Year Progress Report (2019, background): “In contrast, people have rich causal and compositional knowledge of this and many other domains in which they can rapidly learn and use new concepts (Lake et al., 2012).”
One-shot learning by inverting a compositional causal process (2013, methodology): “We used a dataset we collected called “Omniglot” that was designed for studying learning from a few examples [17, 26].”