Untitled

In this paper, a robust knowledge‐based neural‐network model (RKBNN), whose neurons in the hidden layer are all knowledge‐based neurons instead of conventional neurons, is proposed for the microstrip T‐junction structure. The RKBNN model is electromagnetically developed with a set of data that are produced using the method of moments (MoM) method. Through numerical experiments, many advantages have been shown by the RKBNN model over the conventional multilayer perceptron model. © 2004 Wiley Periodicals, Inc. Microwave Opt Technol Lett 42: 257–260, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/mop.20270

show abstract

NNKBN model for the microstrip T-junction structure

Hong

Wang

IEEE Antennas and Propagation Society International Symposium. Digest. Held in Conjunction With: USNC/CNC/URSI North American R

View full text Add to dashboard Cite

A novel thrce-layer neural network w~t h knowlrdpr-based neurons in hidden layer (NNKBNJ has bcen applied to model ihc microstnp T-junction siruciure. The NNKBN model is electromagnelicvlly devcloped wilh a set of data that are praduccd by the MOM method. Numirical expcriment~ show that the NNKBN model has many advantages over the conventional multi-layer perceplron modcl. Keywords Neuron: Microstrip T-junction S

show abstract

Untitled

Cited by 3 publications

References 6 publications

Neural network with knowledge‐based neurons for the modeling of crossover discontinuities in stripline circuits

Neural network with knowledge‐based neurons for the modeling of crossover discontinuities in stripline circuits

Robust knowledge‐based neural‐network model for microstrip T‐junction structure

NNKBN model for the microstrip T-junction structure

Contact Info

Product

Resources

About