DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning

Ellis, Kevin; Wong, Catherine; Nye, Maxwell; Sablé-Meyer, Mathias; Cary, Luc; Morales, Lucas; Hewitt, Luke; Solar-Lezama, Armando; Tenenbaum, Joshua B.

doi:10.1098/rsta.2022.0050

Cited by 15 publications

(7 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our view, capturing the breadth and sophistication of social cognition will require probabilistic generative models of the human intuitive Theory of Mind [143]. Advances in probabilistic programming, program synthesis and neurosymbolic methods [144][145][146][147][148] suggest that the relevant abstractions can be learned combining theory-based inductive constraints and conducive experimental domains [63,[149][150][151][152].…”

Section: Discussionmentioning

confidence: 99%

Emotion prediction as computation over a generative theory of mind

Houlihan

Kleiman-Weiner

Hewitt

et al. 2023

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

From sparse descriptions of events, observers can make systematic and nuanced predictions of what emotions the people involved will experience. We propose a formal model of emotion prediction in the context of a public high-stakes social dilemma. This model uses inverse planning to infer a person’s beliefs and preferences, including social preferences for equity and for maintaining a good reputation. The model then combines these inferred mental contents with the event to compute ‘appraisals’: whether the situation conformed to the expectations and fulfilled the preferences. We learn functions mapping computed appraisals to emotion labels, allowing the model to match human observers’ quantitative predictions of 20 emotions, including joy, relief, guilt and envy. Model comparison indicates that inferred monetary preferences are not sufficient to explain observers’ emotion predictions; inferred social preferences are factored into predictions for nearly every emotion. Human observers and the model both use minimal individualizing information to adjust predictions of how different people will respond to the same event. Thus, our framework integrates inverse planning, event appraisals and emotion concepts in a single computational model to reverse-engineer people’s intuitive theory of emotions. This article is part of a discussion meeting issue ‘Cognitive artificial intelligence’.

show abstract

Section: Discussionmentioning

confidence: 99%

Emotion prediction as computation over a generative theory of mind

Houlihan

Kleiman-Weiner

Hewitt

et al. 2023

Phil. Trans. R. Soc. A.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Symbolic regression uses genetic programming to automatically discover a white-box model of one system ( Angelis et al., 2023 ; Cranmer, 2023 ) – ideal to find the earlier-discussed meta-mechanisms. The DreamCoder system can uncover simple programs that generate example datasets ( Ellis et al., 2023 ). These programs encompass diverse forms, such as regular expressions, graphics, symbolic equations, and physical laws.…”

Section: Nine Simulation Intelligence Motifs For Plant Sciencementioning

confidence: 99%

Plant science in the age of simulation intelligence

Stock,

Pieters,

De Swaef

et al. 2024

Front. Plant Sci.

View full text Add to dashboard Cite

Historically, plant and crop sciences have been quantitative fields that intensively use measurements and modeling. Traditionally, researchers choose between two dominant modeling approaches: mechanistic plant growth models or data-driven, statistical methodologies. At the intersection of both paradigms, a novel approach referred to as “simulation intelligence”, has emerged as a powerful tool for comprehending and controlling complex systems, including plants and crops. This work explores the transformative potential for the plant science community of the nine simulation intelligence motifs, from understanding molecular plant processes to optimizing greenhouse control. Many of these concepts, such as surrogate models and agent-based modeling, have gained prominence in plant and crop sciences. In contrast, some motifs, such as open-ended optimization or program synthesis, still need to be explored further. The motifs of simulation intelligence can potentially revolutionize breeding and precision farming towards more sustainable food production.

show abstract

“…compositional) solutions [62]. This pattern is highly characteristic of more traditional symbolic systems, which also prefer solutions with low description length [63] and have been engineered specifically to 'refactor' their representations during training to decrease description length of more general concepts [64]. [65] go even further in arguing that in-context learning-the primary mechanism via which LLMs exhibit sample efficiency-can be understood as an implicit implementation of more familiar Bayesian inference.…”

Section: (I) Inductive Biasesmentioning

confidence: 99%

Symbols and grounding in large language models

Pavlick

2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Large language models (LLMs) are one of the most impressive achievements of artificial intelligence in recent years. However, their relevance to the study of language more broadly remains unclear. This article considers the potential of LLMs to serve as models of language understanding in humans. While debate on this question typically centres around models’ performance on challenging language understanding tasks, this article argues that the answer depends on models’ underlying competence, and thus that the focus of the debate should be on empirical work which seeks to characterize the representations and processing algorithms that underlie model behaviour. From this perspective, the article offers counterarguments to two commonly cited reasons why LLMs cannot serve as plausible models of language in humans: their lack of symbolic structure and their lack of grounding. For each, a case is made that recent empirical trends undermine the common assumptions about LLMs, and thus that it is premature to draw conclusions about LLMs’ ability (or lack thereof) to offer insights on human language representation and understanding. This article is part of a discussion meeting issue ‘Cognitive artificial intelligence’.

show abstract

DreamCoder: growing generalizable, interpretable knowledge with wake–sleep Bayesian program learning

Cited by 15 publications

References 56 publications

Emotion prediction as computation over a generative theory of mind

Emotion prediction as computation over a generative theory of mind

Plant science in the age of simulation intelligence

Symbols and grounding in large language models

Contact Info

Product

Resources

About