AbstractThis paper argues that a notion of statistical explanation, based on Salmon’s statistical relevance model, can help us better understand deep neural networks. It is proved that homogeneous partitions, the core notion of Salmon’s model, are equivalent to minimal sufficient statistics, an important notion from statistical inference. This establishes a link to deep neural networks via the so-called Information Bottleneck method, an information-theoretic framework, according to which deep neural networks implicitly solve an optimization problem that generalizes minimal sufficient statistics. The resulting notion of statistical explanation is general, mathematical, and subcausal.

中文翻译：

---

了解具有统计相关性的深度学习

摘要本文认为，基于 Salmon 的统计相关模型的统计解释概念可以帮助我们更好地理解深度神经网络。已证明，Salmon 模型的核心概念同质分区等价于最小充分统计量，这是统计推断中的一个重要概念。这通过所谓的信息瓶颈方法（一种信息理论框架）建立了与深度神经网络的链接，根据该方法，深度神经网络隐含地解决了一个优化问题，该问题概括了最小充分统计量。由此产生的统计解释概念是一般的、数学的和次因果的。