A Survey of Complex-Valued Neural Networks
arXiv:2101.12249
Abstract
Artificial neural networks (ANNs) based machine learning models and especially deep learning models have been widely applied in computer vision, signal processing, wireless communications, and many other domains, where complex numbers occur either naturally or by design. However, most of the current implementations of ANNs and machine learning frameworks are using real numbers rather than complex numbers. There are growing interests in building ANNs using complex numbers, and exploring the potential advantages of the so-called complex-valued neural networks (CVNNs) over their real-valued counterparts. In this paper, we discuss the recent development of CVNNs by performing a survey of the works on CVNNs in the literature. Specifically, a detailed review of various CVNNs in terms of activation function, learning and optimization, input and output representations, and their applications in tasks such as signal processing and computer vision are provided, followed by a discussion on some pertinent challenges and future research directions.
arXiv comment15 pages
References in corpus (4)
Cited by in corpus (10)
- Building Blocks for a Complex-Valued Transformer Architecture
- A Spectral-based Physics-informed Finite Operator Learning for Prediction of Mechanical Behavior of Microstructures
- Towards Understanding Theoretical Advantages of Complex-Reaction Networks
- Physics-Informed Holomorphic Neural Networks (PIHNNs): Solving Linear Elasticity Problems
- SignalNet: A Low Resolution Sinusoid Decomposition and Estimation Network
- Complex-valued Federated Learning with Differential Privacy and MRI Applications
- Deep Learning-Based Position Detection for Hydraulic Cylinders Using Scattering Parameters
- SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-space
- Machine Learning Decoder for 5G NR PUCCH Format 0
- The Impact of Feature Representation on the Accuracy of Photonic Neural Networks