This talk presents and discusses advanced neural networks by focusing on complex-valued neural networks (CVNNs) and their applications in coherent imaging. CVNNs are suitable for adaptive processing of complex-amplitude information. Since active imaging deals with coherent electromagnetic wave and light wave, we can expect CVNNs to work more effectively than conventional neural networks or other adaptive methods in real-number framework. Quaternion (or Hypercomplex-valued) neural networks are also discussed in relation to polarization information processing in Poincare sphere parameter space. The beginning half of the Talk is devoted to presentation of the basic idea, overall framework, and fundamental treatment in the CVNNs. We discuss the learning dynamics in the complex domain. The latter half shows an example(s) of CVNN processing in interferometric / polarimetric coherent imaging. We present distortion reduction in phase unwrapping to generate digital elevation model (DEM) from the data obtained by interferometric synthetic aperture radar (InSAR). In polarization SAR (PolSAR), we apply quaternion networks for adaptive classification.