Structure and strength in causal induction.

By T. Griffiths, Josh Tenenbaum. 2005

640 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.

In Artificial Intelligence

Citations in the corpus

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning (2020, background): “(2017), Soft Actor-Critic (SAC) from Haarnoja et al. (2018) and the Twin Delayed DDPG (TD3) from Fujimoto et al.”
Causal Analysis of Agent Behavior for AI Safety (2021, background): “In this case, the first task of the analyst is to discover the behavioral mechanisms through carefully probing the agent with a variety of inputs and recording their responses (Griffiths & Tenenbaum, 2005).”
Structure learning in action (2010, neutral): “Conclusions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .…”
Using Causal Induction in Humans to Learn and Infer Causality from Video (2013, background): “Models such as causal support (Grifﬁths & Tenenbaum, 2005) learn a new, larger model each iteration, and the number of possible models grows exponentially.”
Bayesian learning of visual chunks by human observers (2008, methodology): “Bayesian model comparison, entailing the automatic Occam’s razor effect, and related statistical techniques have been applied with great success to understanding various forms of learning structured information, ranging from classical conditioning in animals (35) to high-level cognitive domains in h”
Learning a theory of causality. (2011, background): “…Waldmann & Martignon, 1998; Steyvers, Tenenbaum, Wagenmakers, & Blum, 2003; Gopnik et al., 2004; Lu, Yuille, Liljeholm, Cheng, & Holyoak, 2008; Griffiths & Tenenbaum, 2005, 2009) has described mathematical models of how children and adults learn domain-specific causal relations by applying…”
Probabilistic models of cognition: exploring representations and inductive biases. (2010, neutral): “compelling quantitative accounts of human causal judgments [22, 25, 26, 27].”
Causal Learning (2012, background): “Griffi ths and Tenenbaum (2005) showed that if one represents uncertainty about the estimates of causal power by a distribution of the likelihood of each possible strength given the data, then Equation 8 and 9, respectively, are maximum likelihood point estimates of the generative and preventive pow”
Causal learning in rats and humans: A minimal rational model (2008, background): “20.1C) is the basic unit in which learning occurs, as has been assumed by previous psychological learning theories (e.g., Cheng, 1997; Griffiths & Tenenbaum, 2005; Rescorla & Wagner, 1972).”
The role of causality in judgment under uncertainty. (2007, methodology): “Causal Bayesian networks have been proposed as tools for understanding how people intuitively learn and reason about causal systems (e.g., Glymour & Cheng, 1998; Gopnik et al., 2004; Griffiths & Tenenbaum, 2005; Sloman & Lagnado, 2005; Steyvers, Tenenbaum, Wagenmakers, & Blum, 2003; Tenenbaum & Gr”
Motor Task Variation Induces Structural Learning (2009, positive): “The principle of structural learning is not confined to the motor system and could also govern processes of perceptual and cognitive learning [31, 32].”
Intuitive Theories (2020, background): “The CBN framework provides a unified account for explaining people's judgments about causal strength (Griffiths & Tenenbaum, 2005) as well as their inferences about how different candidate variables are structurally related (for a review, see Rottman & Hastie, 2013).”
Inferring action structure and causal relationships in continuous sequences of human action. (2015, positive): “To model the generation of causal effects, we use a probabilistic-OR model, commonly used to model human causal inference (Cheng, 1997; Griffiths & Tenenbaum, 2005), in which each potential causal variable has a probability p of being a cause, and each cause has an independent probability x of…”