Applied category theory has recently developed libraries for computing with morphisms in interesting categories, while machine learning has developed ways of learning programs in interesting languages. Taking the analogy between categories and languages seriously, this paper defines a probabilistic generative model of morphisms in free monoidal categories over domain-specific generating objects and morphisms. The paper shows how acyclic directed wiring diagrams can model specifications for morphisms, which the model can use to generate morphisms. Amortized variational inference in the generative model then enables learning of parameters (by maximum likelihood) and inference of latent variables (by Bayesian inversion). A concrete experiment shows that the free category prior achieves competitive reconstruction performance on the Omniglot dataset.
翻译:应用类别理论最近开发了在有趣的类别中以形态论进行计算的各种图书馆,而机器学习则开发了以有趣语言进行学习的方案方法。认真对待类别和语言之间的类比,本文件定义了一种自由的单亚化类别中形态学的概率基因模型,相对于特定领域生成物体和形态学而言。论文展示了循环导电图如何为形态学设计规格,该模型可以用来产生形态学。基因模型中的混合变异推论随后使得能够学习参数(尽可能地)和潜在变量的推论(Bayesian insversion )。具体实验显示,自由类别以前在Omniglot数据集上取得了竞争性重建业绩。