Complex-Valued Neural Networks for Wave-Based Realization of Reservoir Computing

Akira Hirose, Seiji Takeda, Toshiyuki Yamane, Daiju Nakano, Shigeru Nakagawa, Ryosho Nakane, Gouhei Tanaka

Abstract: In this paper, we discuss the significance of complex-valued neural-network (CVNN) framework in energy-efficient neural networks, in particular in wave-based reservoir networks. Physical-wave reservoir networks are highly enhanced by CVNNs. From this viewpoint, we also compare the features of reservoir computing and other architectures.