论文标题
组成活性推理II：多项式动力学。近似推理学说
Compositional Active Inference II: Polynomial Dynamics. Approximate Inference Doctrines
论文作者
论文摘要
我们使用新的近似推理学说的概念来开发活动推断的组成理论，将统计游戏与播放它们的动力学系统的功能联系起来。为了展示此类函子，我们首先使用多项式函数的语言的概括来提供必要类型的组合界面的概括：构建了所需类型类型的组成界面：构建了colgebras的多项式索引类别，我们构建了不同的和动态的``s systrical''sycription toctrictrictictrictrictictrictrictictrictic nostrictic nostrictic nostrictic nostrictic insectrimations interctrimations。然后，我们描述``外部参数化''统计游戏，并使用它们来构建两个在计算神经科学文献中发现的近似推理学说，我们称之为“ laplace”和``laplace''和``hebb-laplace''教义：前者生成的动态系统，可最大化高斯模型的后代；后者产生的系统还优化了确定其预测的参数（或“权重”）。
We develop the compositional theory of active inference by introducing activity, functorially relating statistical games to the dynamical systems which play them, using the new notion of approximate inference doctrine. In order to exhibit such functors, we first develop the necessary theory of dynamical systems, using a generalization of the language of polynomial functors to supply compositional interfaces of the required types: with the resulting polynomially indexed categories of coalgebras, we construct monoidal bicategories of differential and dynamical ``hierarchical inference systems'', in which approximate inference doctrines have semantics. We then describe ``externally parameterized'' statistical games, and use them to construct two approximate inference doctrines found in the computational neuroscience literature, which we call the `Laplace' and the `Hebb-Laplace' doctrines: the former produces dynamical systems which optimize the posteriors of Gaussian models; and the latter produces systems which additionally optimize the parameters (or `weights') which determine their predictions.
