𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Explanation facility for neural networks

✍ Scribed by L. F. Pau; T. Götzsche

Publisher
Springer Netherlands
Year
1992
Tongue
English
Weight
615 KB
Volume
5
Category
Article
ISSN
0921-0296

No coin nor oath required. For personal study only.

✦ Synopsis

This paper give a methodology, PROLOG code, as well as an example of an explanation facility EN applicable to most neural networks. It involves How?, Why? and TRACE facilities, and is based on a general explanation degree calculation in a multilayer neural network, as well as on input node characterization grammars for synthesis of explanation text.

📜 SIMILAR VOLUMES

An explanation of reasoning neural netwo
An explanation of reasoning neural networks
✍ R.R. Tsaih 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 693 KB

tioning Neural Networks (RN) adopts the layered feedforward network structure, and its learning algorithm belongs to the weight-and-structure-change category of learning algorithm. In this paper, we firstly explain that, in the layered feedforward network, the essential characteristic of the mapping

Safety-critical neural computing: explan
Safety-critical neural computing: explanation and verification in knowledge augmented neural networks
✍ J.H. Johnson; P.D. Picton; N.J. Hallam 📂 Article 📅 1993 🏛 Elsevier Science 🌐 English ⚖ 601 KB

This paper addresses the problem that conventional neural networks cannot contain a priori knowledge and cannot explain their output. A mathematical theory of 'black-box classifiers' is developed which covers most of the best known neural architectures. The limitations of the non-model based computa