On Energy Function for Complex-Valued Neural Networks

Complex-Valued Neural Networks

The usual real-valued artificial neural networks have been applied to various fields such as telecommunications, robotics, bioinformatics, image processing and speech recognition, in which complex numbers (two dimensions) are often used with the Fourier transformation. This indicates the usefulness of complex-valued neural networks whose input and output signals and parameters such as weights a...

Complex-Valued Neural Networks

On Complex Valued Convolutional Neural Networks

Convolutional neural networks (CNNs) are the cutting edge model for supervised machine learning in computer vision. In recent years CNNs have outperformed traditional approaches in many computer vision tasks such as object detection, image classification and face recognition. CNNs are vulnerable to overfitting, and a lot of research focuses on finding regularization methods to overcome it. One ...

Novel Complex Valued Neural Networks

In view of many applications, in recent years, there has been increasing interest in complex valued neural networks. In this paper, it is reasoned that transforming real valued signals into complex valued signals (using Discrete Fourier Transform) and processing them in that domain is equivalent to processing real valued signals. This approach could have many advantages. Also neural networks ba...

Multiple-valued energy function in neural networks with asymmetric connections.

We apply the graphic transformation method[11],[25] to obtain the steady state distribution of asymmetric Boltzmann machines as an extension of the symmetric equilibrium case. We give the magnitude of deviation from the equilibrium explicitly as a function of the asymmetry in the connections between the neurons. We show that the steady state of asymmetric Boltzmann machines is characterized by ...