Title :
Neuromodeling of microwave circuits exploiting space mapping technology
Author :
Bandler, J.W. ; Ismail, M.A. ; Rayas-Sanchez, J.E. ; Zhang, Q.J.
Author_Institution :
Dept. of Electr. & Comput. Eng., McMaster Univ., Hamilton, Ont., Canada
Abstract :
Space mapping (SM) technology based neuromodels decrease the cost of training, improve generalization ability and reduce the complexity of the ANN topology w.r.t. classical neuromodeling. Three novel techniques are proposed to generate SM based neuromodels: space-mapped neuromodeling (SMN), frequency dependent space-mapped neuromodeling (FDSMN), and frequency-space-mapped neuromodeling (FSMN). Huber optimization is proposed to train the neuro-space-mapping (NSM). The techniques are illustrated by a microstrip right angle bend.
Keywords :
circuit CAD; circuit optimisation; generalisation (artificial intelligence); microstrip circuits; microwave circuits; neural nets; ANN topology; Huber optimization; frequency dependent techniques; frequency-space-mapped techniques; generalization ability; microstrip right angle bend; microwave circuits; neuromodeling; space mapping technology; Artificial neural networks; Circuit simulation; Circuit topology; Computational modeling; Frequency; Mathematical model; Microwave circuits; Microwave technology; Samarium; Space technology;
Conference_Titel :
Microwave Symposium Digest, 1999 IEEE MTT-S International
Conference_Location :
Anaheim, CA, USA
Print_ISBN :
0-7803-5135-5
DOI :
10.1109/MWSYM.1999.779445
