贝叶斯反射:一种人工智能的预测编码引擎
The Bayesian Reflex: A Predictive Coding Engine for Artificial Intelligence
浏览论文内容
中文总结 AI 辅助
该研究提出贝叶斯反射计算框架,结合预测编码三大支柱,利用近期算法突破实现可扩展的类脑持续学习、感知与决策,通过多领域应用为自适应AI提供蓝图。
中文摘要 AI 辅助
预测编码为大脑皮层计算提供了强大的理论,但人工智能领域中对应的可扩展算法实现一直难以实现。本文提出贝叶斯反射这一计算框架,它通过三大支柱直接实例化预测编码:基于分层生成模型的信念维护、通过预测误差最小化实现的序贯贝叶斯更新,以及通过主动推理实现的不确定性驱动行动。我们表明,近期的突破——用于精确独立同分布(i.i.d.)采样的椭球分解、用于深度分层推理的递归高斯过程,以及可感知导数的贝叶斯优化——提供了缺失的算法要素。该框架支持数学上严谨、可扩展且受大脑启发的持续学习、感知与决策,我们通过从气候模型评估到素数发现的应用展示其通用性,为真正自适应的人工智能提供蓝图。
英文摘要
Predictive coding offers a powerful theory of cortical computation, but corresponding scalable algorithmic implementations for artificial intelligence have remained elusive. This paper introduces the Bayesian reflex, a computational framework that directly instantiates predictive coding through three pillars: belief maintenance via hierarchical generative models, sequential Bayesian updating via prediction-error minimization, and uncertainty-driven action via active inference. We show that recent breakthroughs---ellipsoidal decomposition for exact $i.i.d.$ sampling, recursive Gaussian processes for deep hierarchical inference, and derivative-aware Bayesian optimization---provide the missing algorithmic ingredients. The resulting framework enables mathematically principled, scalable, and brain-inspired continual learning, perception, and decision-making. We illustrate its versatility through applications ranging from climate model evaluation to prime number discovery, offering a blueprint for truly adaptive artificial intelligence.
发表机构
- Indian Statistical Institute(印度统计研究所)
机构由 AI 辅助整理,请以论文原文为准。