Theory learning as stochastic search in the language of thought

By Tomer D. Ullman, Noah D. Goodman, Josh Tenenbaum. 2012

101 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cultural Studies, Developmental and Educational Psychology

How researchers see this paper

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

In Artificial Intelligence

In Cultural Studies

In Developmental and Educational Psychology

Citations in the corpus

Finding new facts; thinking new thoughts. (2012, background): “3 The computational proposals echo this insofar as variables get their meaning from their relationship to other terms in the theory grammar and serve as placeholder concepts (Goodman et al., 2011; Ullman et al., 2012).”
On the nature and origin of intuitive theories : learning, physics and psychology (2015, background): “The core of our formal treatment is a hierarchical probabilistic generative model for theories [92, 187, 62], specialized to the domain of intuitive physical theories (Fig.”
Mind Games: Game Engines as an Architecture for Intuitive Physics. (2017, background): “Even in inference tasks where physics engines can be useful for evaluating candidate hypotheses or explanations, there remains the di ﬃ cult and separate problem of coming up with the right hypotheses in the ﬁrst place [84, 32, 85].”
Neuronal boost to evolutionary dynamics (2015, background): “The mechanisms for generating variability in neural spiking patterns are relatively simple to rationalize, and there are many works in the literature that take this aspect as a modelling objective [12].”
Formalizing Neurath’s Ship: Approximate Algorithms for Online Causal Learning (2016, background): “…Lucas, Williams, & Kalish, 2009); hierarchical organization (Griffiths & Tenenbaum, 2009; Williamson & Gabbay, 2005); and temporal (Pacer & Griffiths, 2012) and spatial (Battaglia, Hamrick, & Tenenbaum, 2013; Ullman et al., 2012; Ullman, Stuhlmüller, Goodman, & Tenenbaum, 2014) semantics.”
Imagination and the generation of new ideas (2015, background): “Along the lines of the “inner loop” proposed in theoryguided stochastic search (Ullman et al., 2012), once generated, any hypothesis can be subject to factchecking by assessing the extent to which it predicts observed data.”