用贝叶斯反射框架实现类脑持续学习与决策
The Bayesian Reflex: A Predictive Coding Engine for Artificial Intelligence
- 基于生成模型与预测误差最小化，实现层级信念更新
- 结合椭球分解与递归高斯过程，支持高效采样与推理
- 适合追求可解释性与自适应能力的智能系统研究者
预测编码为皮层计算提供了强大理论，但其在人工智能中的可扩展算法实现仍不明确。本文提出贝叶斯反射框架，通过三大支柱实现：基于分层生成模型的信念维持、通过预测误差最小化进行序列贝叶斯更新，以及基于不确定性的主动推理驱动行动。我们发现，近期突破——椭球分解实现精确独立同分布采样、递归高斯过程支持深层层级推断、导数感知贝叶斯优化——填补了算法关键空白。该框架实现了数学严谨、可扩展且类脑的持续学习、感知与决策。应用涵盖气候模型评估到素数发现，为真正自适应的人工智能提供蓝图。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。