Automated Knowledge-Based Neural Network Modeling for Microwave Applications

• Published in: IEEE microwave and wireless components letters Vol. 24; no. 7; pp. 499 - 501
• Main Author: Zhang, Qi Jun
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.07.2014; Institute of Electrical and Electronics Engineers
• Subjects: Accuracy; Adaptation models; Adaptive sampling; Applied sciences; Artificial intelligence; Automated; Computer science; control theory; systems; Connectionism. Neural networks; Data models; Design automation; Exact sciences and technology; Integrated circuit modeling; Knowledge base; Knowledge based systems; knowledge-based neural network (KBNN); Mathematical models; Microwave theory and techniques; Microwaves; modeling; Neural networks; optimization; Training; Training data; Automation; Design automation; Knowledge representation; Microwave; Knowledge base; Neural network; Modeling; Adaptive method; Optimization; knowledge-based neural network (KBNN); Data distribution; Data models; Sampling; Data structure
• ISSN: 1531-1309; 1558-1764
• DOI: 10.1109/LMWC.2014.2316251

Automated model generation (AMG) method is extended from generating pure neural network (NN) models to generating knowledge-based NN models. Knowledge-based models have been demonstrated in the existing literature to use less data over pure NN models while maintaining good accuracy. The proposed method automates data generation, determination of data distribution, model structure adaptation, and model training in a systematic framework. It can further reduce the number of training data through the adaptive sampling process, shorten the model development time over existing AMG methods and existing knowledge-based modeling methods, and ensure the accuracy of the final model at the same time. The algorithm is demonstrated through microwave modeling examples.