Extended Bayesian inference incorporating symmetry bias

Shuji Shinohara*, Nobuhito Manome, Kouta Suzuki, Ung il Chung, Tatsuji Takahashi, Pegio Yukio Gunji, Yoshihiro Nakajima, Shunji Mitsuyoshi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)


We start by proposing a causal induction model that incorporates symmetry bias. This model has two parameters that control the strength of symmetry bias and includes conditional probability and conventional models of causal induction as special cases. We calculated the determination coefficients between assessments by participants in eight types of causal induction experiments and the estimated values using the proposed model. The mean coefficient of determination was 0.93. Thus, it can reproduce causal induction of human judgment with high accuracy. We further propose a human-like Bayesian inference method to replace the conditional probability in Bayesian inference with the aforementioned causal induction model. In this method, two components coexist: the component of Bayesian inference, which updates the degree of confidence for each hypothesis, and the component of inverse Bayesian inference that modifies the model of each hypothesis. In other words, this method allows not only inference but also simultaneous learning. Our study demonstrates that the method addresses unsteady situations where the target of inference occasionally changes not only by making inferences based on knowledge (model) and observation data, but also by modifying the model itself.

Original languageEnglish
Article number104104
Publication statusPublished - 2020 Apr


  • Bayesian inference
  • Causal inference
  • Discounting learning algorithm
  • Learning
  • Non-stationary situation
  • Symmetry inference

ASJC Scopus subject areas

  • Statistics and Probability
  • Modelling and Simulation
  • Biochemistry, Genetics and Molecular Biology(all)
  • Applied Mathematics


Dive into the research topics of 'Extended Bayesian inference incorporating symmetry bias'. Together they form a unique fingerprint.

Cite this