In this paper we discuss the relationships between conditional and preferential logics and neural network models, based on a multi-preferential semantics. We propose a concept-wise multipreference semantics, recently introduced for defeasible description logics to take into account preferences with respect to different concepts, as a tool for providing a semantic interpretation to neural network models. This approach has been explored both for unsupervised neural network models (Self-Organising Maps) and for supervised ones (Multilayer Perceptrons), and we expect that the same approach might be extended to other neural network models. It allows for logical properties of the network to be checked (by model checking) over an interpretation capturing the input-output behavior of the network. For Multilayer Perceptrons, the deep network itself can be regarded as a conditional knowledge base, in which synaptic connections correspond to weighted conditionals. The paper describes the general approach, through the cases of Self-Organising Maps and Multilayer Perceptrons, and discusses some open issues and perspectives.
翻译:在本文中,我们讨论了基于多优先语义学的有条件和优惠逻辑和神经网络模型之间的关系。我们建议了一种基于多优先语义学的多角度多角度参考语义学,这是最近为不可行的描述逻辑而引入的,以考虑到对不同概念的偏好,作为向神经网络模型提供语义解释的工具。这一方法已经探讨过,既针对不受监督的神经网络模型(自组织地图),也针对受监督的神经网络模型(多层天体),我们期望同一方法可以推广到其他神经网络模型。它允许对网络的逻辑属性进行检查(通过模式检查),而不是对获取网络投入-输出行为的解释进行检查。对于多层 Perceptron来说,深层网络本身可以被视为一个有条件的知识基础,其中的合成连接与加权条件相对应。该文件描述了通过自操作地图和多层摄像等实例的一般方法,并讨论了一些开放的问题和观点。