✦ LIBER ✦

Use of neural networks for compiling diagnostic rules

✍ Scribed by V. G. Shchetinin; A. I. Brazhnikov

Publisher: Springer US
Year: 2000
Tongue: English
Weight: 643 KB
Volume: 34
Category: Article
ISSN: 0006-3398
DOI: 10.1007/bf02385220

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Rule extraction: Using neural networks o

Rule extraction: Using neural networks or for neural networks?

✍ Zhi-Hua Zhou 📂 Article 📅 2004 🏛 Springer 🌐 English ⚖ 442 KB

DIAGNOSTIC RULE EXTRACTION FROM TRAINED

DIAGNOSTIC RULE EXTRACTION FROM TRAINED FEEDFORWARD NEURAL NETWORKS

✍ YIMIN FAN; C.JAMES LI 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 272 KB

This paper describes a method of extracting diagnostic rules from trained diagnostic feedforward neural nets that are constructed to recognise di!erent mechanical faults using automated weight and structure learning algorithms. The rule extracting method is based on an interpretation that considers

On rule pruning using fuzzy neural netwo

On rule pruning using fuzzy neural networks

✍ Nikhil R. Pal; Tandra Pal 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 815 KB

Shann and Fu (SF) proposed a fuzzy neural network (FNN) for role pruning in a fuzzy controller. In this paper we first analyze the FNN of SF and discuss some of its limitations. SF attempted to eliminate redundant rules interpreting some of the connection weights as certainty factors of rules. In th

Neural networks for control, robotics an

Neural networks for control, robotics and diagnostics

✍ Changyin Sun; Wen Yu 📂 Article 📅 2008 🏛 Springer-Verlag 🌐 English ⚖ 78 KB

Using neural networks as a tool for cons

Using neural networks as a tool for constructing rule based systems

✍ G.P. Fletcher; C.J. Hinde 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 525 KB

Discretizing continuous neural networks

Discretizing continuous neural networks using a polarization learning rule

✍ Lifeng Wang; H.D. Cheng 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 661 KB

Discrete neural networks are simpler than their continuous counterparts, can obtain more stable solutions, and their hidden layer representations are easier to interpret. This paper presents a polarization learning rule for discretizing multi-layer neural networks with continuous activation function