.png){kind=icon}
返回
Bayes and Darwin: How replicator populations implement Bayesian computations
.png){kind=icon}
OA
AI
DOI：10.1002/bies.202100255.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Bayesian learning theory and evolutionary theory both formalize adaptive competition dynamics in possibly high-dimensional, varying, and noisy environments. What do they have in common and how do they differ? In this paper, we discuss structural and dynamical analogies and their limits, both at a computational and an algorithmic-mechanical level. We point out mathematical equivalences between their basic dynamical equations, generalizing the isomorphism between Bayesian update and replicator dynamics. We discuss how these mechanisms provide analogous answers to the challenge of adapting to stochastically changing environments at multiple timescales. We elucidate an algorithmic equivalence between a sampling approximation, particle filters, and the Wright-Fisher model of population genetics. These equivalences suggest that the frequency distribution of types in replicator populations optimally encodes regularities of a stochastic environment to predict future environments, without invoking the known mechanisms of multilevel selection and evolvability. A unified view of the theories of learning and evolution comes in sight.
Keyword:
adaptation
Bayesian inference
graphical models
particle filters
replicator dynamics
期刊
IF:
2.7
论文数:
4.7K
被引数:
1.0W
机构
暂无机构信息
引用论文
.png){kind=icon}
GDF‐5/7 and bFGF activate integrin α2‐mediated cellular migration in rabbit ligament fibroblastsOAAI
OAAI分享收藏The Cognitive Lens: a primer on conceptual tools for analysing information processing in developmental and regenerative morphogenesis认知透镜: 用于分析发育和再生形态发生中信息处理的概念工具的入门
OAAI
OAAI分享收藏
查看更多内容