Surrogate‐based model using auto‐encoder for optimising multi‐band antennas

This paper suggests an optimisation method to design multi-band antenna using artificial neural networks. The proposed network, surrogate-based model auto-encoder (SBM-AE), is composed of two parts, ordinary network and auto-encoder. First, the front predicts encoded characteristics then decodes predicted data obtain characteristics. After training encoder a characteristic signature vector, regresses only vectors, reducing complexity number parameters network. not reduces time but also significantly required. We confirm effectiveness by designing where SBM-AE required 270 while conventional without needed 1350 achieve comparatively same error rate.