Search Results for author: David Kinney

Found 3 papers, 0 papers with code

Causal Feature Learning for Utility-Maximizing Agents

no code implementations18 May 2020 David Kinney, David Watson

We propose a new technique, pragmatic causal feature learning (PCFL), which extends the original CFL algorithm in useful and intuitive ways.

Noisy Deductive Reasoning: How Humans Construct Math, and How Math Constructs Universes

no code implementations28 Oct 2020 David H. Wolpert, David Kinney

We present a computational model of mathematical reasoning according to which mathematics is a fundamentally stochastic process.

Math Mathematical Reasoning

Causal Theories and Structural Data Representations for Improving Out-of-Distribution Classification

no code implementations18 Sep 2023 Donald Martin, Jr., David Kinney

Specifically, we use simulated data to show that training a neural network with a data representation that makes explicit the invariant structural causal features of the data generating process of an epidemic system improves out-of-distribution (OOD) generalization performance on a classification task as compared to a more naive approach to data representation.

Cannot find the paper you are looking for? You can Submit a new open access paper.