Name
Abstract | ||
|---|---|---|
Embedding prior knowledge has been an important way to enhance generalization capability and training efficiency of neural networks. In this paper a knowledge network is presented to incorporate prior knowledge in the form of continuous multidimensional nonlinear functions, which are typically obtained from engineering empirical experience and can be highly nonlinear. This type of network addresses some of the bottlenecks, i.e., reliability of model and limited training data, in the growing use of neural networks in providing multidimensional continuous nonlinear models for many engineering problems. Practical electrical engineering modeling examples have been used to demonstrate the enhanced accuracy of the proposed network as compared with conventional neural model approach. |
Year | DOI | Venue |
|---|---|---|
1997 | 10.1109/ICNN.1997.611676 | 1997 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS 1-4 |
Keywords | Field | DocType |
data engineering,learning artificial intelligence,knowledge engineering,neural networks,electromagnetic modeling,generalization,neural network,neural nets,function approximation,reliability engineering,electrical engineering,network topology,multidimensional systems,training data,knowledge based systems | Training set,Nervous system network models,Nonlinear system,Embedding,Function approximation,Computer science,Knowledge-based systems,Artificial intelligence,Artificial neural network,Machine learning | Conference |
Citations | PageRank | References |
1 | 0.36 | 3 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fang Wang | 1 | 80 | 8.90 |
| Q.J. Zhang | 2 | 5 | 3.17 |