Formalizing Neurath’s Ship: Approximate Algorithms for Online Causal Learning

By Neil R. Bramley, Peter S. Dayan, T. Griffiths, David A. Lagnado. 2016

142 citations recorded by the source corpus.

Higher-level cognition depends on the ability to learn models of the world. We can characterize this at the computational level as a structure-learning problem with the goal of best identifying the prevailing causal relationships among a set of relata. However, the computational cost of performing exact Bayesian inference over causal models grows rapidly as the number of relata increases. This implies that the cognitive processes underlying causal learning must be substantially approximate. A powerful class of approximations that focuses on the sequential absorption of successive inputs is captured by the Neurath’s ship metaphor in philosophy of science, where theory change is cast as a stochastic and gradual process shaped as much by people’s limited willingness to abandon their current theory when considering alternatives as by the ground truth they hope to approach. Inspired by this metaphor and by algorithms for approximating Bayesian inference in machine learning, we propose an algorithmic-level model of causal structure learning under which learners represent only a single global hypothesis that they update locally as they gather evidence. We propose a related scheme for understanding how, under these limitations, learners choose informative interventions that manipulate the causal system to help elucidate its workings. We find support for our approach in the analysis of 3 experiments.

Subfields: Artificial Intelligence, History and Philosophy of Science

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 History and Philosophy of Science

Citations in the corpus

Causal Reasoning from Meta-reinforcement Learning (2019, background): “Despite advances in both (Ortega and Stocker, 2015; Lattimore et al., 2016; Bramley et al., 2017; Forney et al., 2017; Sen et al., 2017; Parida et al., 2018), inducing models is expensive and typically requires simplifying assumptions.”
Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense (2020, background): “vention, which enables agents to explore possible directions of undirected causal edges [153, 154].”
Challenges and Future Directions of Big Data and Artificial Intelligence in Education (2020, background): “…on deploying AI in education is gradually shifting from a computational focus that demonstrates use cases of new technology to cognitive focus that incorporates cognition in its design, such as perception (VanRullen, 2017), emotion (Song et al., 2016), and cognitive thinking (Bramley et al., 2017).”