Concepts in a Probabilistic Language of Thought

By Noah D. Goodman, Josh Tenenbaum, Tobias Gerstenberg. 2014

147 citations recorded by the source corpus.

Note: The book chapter is reprinted courtesy of The MIT Press, from the forthcoming edited collection “The Conceptual Mind: New Directions in the Study of Concepts” edited by Eric Margolis and Stephen Laurence, print date Spring 2015.

Subfields: Artificial Intelligence, Developmental and Educational Psychology, History and Philosophy of Science, Cognitive Science & 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 Developmental and Educational Psychology

In History and Philosophy of Science

In Cognitive Science & Psychology

Citations in the corpus

Language Model Cascades (2022, background): “Recent advances in program synthesis suggest the possibility of probabilistic program induction (Lake et al., 2015; Goodman et al., 2014) to search for cascades which solve a target task, rather than assuming a ﬁxed probabilistic program structure.”
Relational inductive biases, deep learning, and graph networks (2018, background): “Programs and more “computer-like” processing can oﬀer greater representational and computational expressivity with respect to these notions, and some have argued they are an important component of human cognition (Tenenbaum et al., 2011; Lake et al., 2015; Goodman et al., 2015).”
The Naïve Utility Calculus: Computational Principles Underlying Commonsense Psychology. (2016, background): “Its formulation as an intuitive theory was anticipated in some form by pioneers in social cognition Fritz Heider [38], Harold Kelley [39], and Roger Brown [40], but with the development of new computational cognitive modeling tools these ideas can be formulated and tested more precisely [41-46].”
Beyond imitation: Zero-shot task transfer on robots by learning concepts as cognitive programs (2018, background): “Representing concepts as programsmakes them naturally compositional as required for a language of thought (57), and programs provide explainability that has been lacking in current black-box policy learning methods.”
Leveraging Language to Learn Program Abstractions and Search Heuristics (2021, background): “The hierarchical Bayesian framing also draws connections to computational cognitive models which model human conceptual representations and learning (Goodman et al., 2014; Fodor, 1975; Rule, 2020) as inference over program-like representations.”
On the nature and origin of intuitive theories : learning, physics and psychology (2015, unknown): “We can express all of this knowledge in terms of a probabilistic program in a language such as Church [58, 59].”
Question Asking as Program Generation (2017, background): “Machine systems for question answering have also fruitfully modeled questions as programs [24, 12], and computational work in cognitive science has modeled various kinds of concepts as programs [17, 5, 13].”
Formal Distributional Semantics: Introduction to the Special Issue (2016, background): “…Linguistics should work on general language understanding, that is, on theories and models that account both for language use as a whole, and for the associated conceptual apparatus (Collobert and Weston 2008; Mikolov, Joulin, and Baroni 2015; Goodman, Tenenbaum, and Gerstenberg 2015; Erk 2016).”
Causal superseding. (2015, background): “This claim about the impact of norm violations on counterfactual thinking has played a role in some existing theoretical work in causal cognition (Halpern & Hitchcock, 2014; Hitchcock & Knobe, 2009; Knobe & Szabó, 2013), and it forms the second piece of our explanation of causal superseding.”
Intuitive Theories (2020, background): “We have suggested that people’s intuitive domain theories are best understood in terms of probabilistic, generative programs (Goodman et al., 2015).”