Novel Complex-Valued Hopfield Neural Networks with Phase and Magnitude Quantization
This work addresses a domain-specific problem for researchers in neural networks, offering an incremental improvement in state capacity.
The researchers tackled the problem of limited states in complex-valued Hopfield neural networks by introducing two new models with phase and magnitude quantization, resulting in a significant increase in the number of states compared to existing models.
This research paper introduces two novel complex-valued Hopfield neural networks (CvHNNs) that incorporate phase and magnitude quantization. The first CvHNN employs a ceiling-type activation function that operates on the rectangular coordinate representation of the complex net contribution. The second CvHNN similarly incorporates phase and magnitude quantization but utilizes a ceiling-type activation function based on the polar coordinate representation of the complex net contribution. The proposed CvHNNs, with their phase and magnitude quantization, significantly increase the number of states compared to existing models in the literature, thereby expanding the range of potential applications for CvHNNs.