The Free-Energy-Principle (FEP) is an influential and controversial theory which postulates a deep and powerful connection between the stochastic thermodynamics of self-organization and learning through variational inference. Specifically, it claims that any self-organizing system which can be statistically separated from its environment, and which maintains itself at a non-equilibrium steady state, can be construed as minimizing an information-theoretic functional -- the variational free energy -- and thus performing variational Bayesian inference to infer the hidden state of its environment. This principle has also been applied extensively in neuroscience, and is beginning to make inroads in machine learning by spurring the construction of novel and powerful algorithms by which action, perception, and learning can all be unified under a single objective. While its expansive and often grandiose claims have spurred significant debates in both philosophy and theoretical neuroscience, the mathematical depth and lack of accessible introductions and tutorials for the core claims of the theory have often precluded a deep understanding within the literature. Here, we aim to provide a mathematically detailed, yet intuitive walk-through of the formulation and central claims of the FEP while also providing a discussion of the assumptions necessary and potential limitations of the theory. Additionally, since the FEP is a still a living theory, subject to internal controversy, change, and revision, we also present a detailed appendix highlighting and condensing current perspectives as well as controversies about the nature, applicability, and the mathematical assumptions and formalisms underlying the FEP.
翻译:自由能源原则(FEP)是一个具有影响力和争议性的理论,它假定自我组织和通过变推论学习的随机热动力学和热力学之间有着深刻和强大的联系。 具体地说,它声称,任何在统计上可以与其环境分离的自我组织系统,并且维持在非平衡稳定状态的自我组织系统,都可以被解释为最大限度地减少信息理论功能 -- -- 变异自由能源 -- -- 并因此对推断其环境的隐蔽状态进行不同的巴耶斯推理。 这一原则在神经科学中也得到了广泛应用,并且正在通过推动构建新的和强大的算法,使行动、认知和学习都能够在单一的目标下统一起来。 虽然其扩张性和通常宏大的主张在哲学和理论神经科学中引起了重大的辩论,数学深度和缺乏可获取的介绍和教义,从而往往无法在文献中深入理解。 我们的目的是通过构建一个数学和强大的数学视角学习,同时提供当前、深入的理论的理论性推理学理论, 也是我们目前对EP的理论的理论的理论的理论的理性,作为核心的推理判, 和理论的理论的理论的争论,作为我们目前和理论的理论的理论的理论的推理論的争论, 的争论的争论的争论,作为现在的理论的争论, 的理论的理论的理论的争论, 的争论的争论, 也是, 的理论的理论的理论的推论论的理论的推论的推论的推论, 的推论, 的推论的推论的推论的推论,作为我们的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论,我们的推论的推论,我们的推论, 的推论, 的推论的推论的推论和推论,作为的推论,作为的推论,作为的推论,作为的推论,作为的推论,作为的推论,作为的推论的推论的推论的推论的推论的推论的推论的推论的推论的推论,我们的推论的推论的推论的推论的推论