Fig. 2: Designed neural network for left reflection to transmission mapping.
From: Machine learning for knowledge acquisition and accelerated inverse-design for non-Hermitian systems
a Architecture of the optimized network, showing the left reflection RL as function of frequency ω as input and the predicted transmission \(\hat{T}\) as function of ω as output. b Histogram of the spectral prediction error. c Three representative examples for generation of transmission response T (using Transfer Matrix Method: TMM and Machine Learning: ML) from three different given reflection spectra RL versus normalized frequency ωa/2πc, with a the dimension of the scatterer and c the speed of light in free space. The solid red and dotted black line represent the transmission calculated from TMM and ML method, respectively. More examples are shown in Supplementary Fig. 1.
