Complex-Valued Neural Networks: A Comprehensive Survey

Lee, ChiYan; Hasegawa, Hideyuki; Gao, Shangce

doi:10.1109/jas.2022.105743

Cited by 84 publications

(18 citation statements)

References 191 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although complex activation functions used on CVNN are numerous [34], we will mainly focus on two types of activation functions that are an extension of the real-valued functions [4], [35]:…”

Section: Model Architecturesmentioning

confidence: 99%

Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks

Barrachina

Ren

Morisseau

et al. 2023

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

In this paper, we investigated the semantic segmentation of Polarimetric Synthetic Aperture Radar (PolSAR) using Complex-Valued Neural Network (CVNN). Although the coherency matrix is more widely used as the input of CVNN, the Pauli vector has recently been shown to be a valid alternative. We exhaustively compare both methods for six model architectures, three complex-valued, and their respective real-equivalent models. We are comparing, therefore, not only the input representation impact but also the complex-against the real-valued models. We then argue that the dataset splitting produces a high correlation between training and validation sets, saturating the task and thus achieving very high performance. We, therefore, use a different data pre-processing technique designed to reduce this effect and reproduce the results with the same configurations as before (input representation and model architectures). After seeing that the performance per class is highly different according to class occurrences, we propose two methods for reducing this gap and performing the results for all input representations, models, and dataset preprocessing.

show abstract

Section: Model Architecturesmentioning

confidence: 99%

Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks

Barrachina

Ren

Morisseau

et al. 2023

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

show abstract

“…Therefore, MCSMA can be applied to the present engineering and practical fields with desirable results tentatively in the future [56,57]. most primitive linear threshold artificial neural network models, many new network models with innovative structures and simulations of human brain structures have emerged [58,59]. Dendritic neuron model(DNM) is a single neural network model that simulates the primitive dendritic structure of a nerve cell.…”

Section: Engineering Practical Problem Testmentioning

confidence: 99%

Maximum Lyapunov Exponent-based Multiple Chaotic Slime Mold Algorithm for Real-world Optimization

Yang

Jin

Lei

et al. 2023

Preprint

View full text Add to dashboard Cite

Slime mold algorithm (SMA) is a nature-inspired algorithm that simulates the biological optimization mechanisms and has achieved great results in various complex stochastic optimization problems. Owing to the simulated biological search principle of slime mold, SMA has a unique advantage in global optimization problem. However, it still suffers from issues of missing the optimal solution or collapsing to local optimum when facing complicated problems. To conquer these drawbacks, we consider adding a novel multi-chaotic local operator to the bio-shock feedback mechanism of SMA to compensate for the lack of exploration of the local solution space with the help of the perturbation nature of the chaotic operator. Based on this, we propose an improved algorithm, namely MCSMA, by investigating how to improve the probabilistic selection of chaotic operators based on the maximum Lyapunov exponent (MLE), an inherent property of chaotic maps. We implement the comparison between MCSMA with other state-of-the-art methods on IEEE Congress on Evolution Computation (CEC) i.e., CEC2017 benchmark test suits and CEC2011 practical problems to demonstrate its potency and perform dendritic neuron model training to test the robustness of MCSMA on classification problems. Finally, the parameters' sensitivities of MCSMA, the utilization of the solution space, and the effectiveness of the MLE are adequately discussed.

show abstract

“…Complex-valued NN is an extended NN model to complex domain that can deal with complexvalued signals or 2D signals naturally where the parameters such as weights and biases are all complex numbers, and the activation function of each complex-valued neuron is a complex function inevitably. The complex-valued NN has been applied to a variety of fields such as signal processing, image processing, optoelectronics, associative memories, adaptive filters, telecommunications, and privacy protection [1,[16][17][18][19][20][21][22][23][24].…”

Section: Complex-valued Neural Network and Learning Algorithmsmentioning

confidence: 99%

“…Complex-valued neural network is an extension of the real-valued neural network to the complex domain and has been applied in various fields [1]. Neural network is abbreviated to NN hereafter.…”

Section: Introductionmentioning

confidence: 99%

Proposal of fully augmented complex-valued neural networks

Nitta

2023

NOLTA

View full text Add to dashboard Cite

In this paper, we propose a complex-valued neural network based on the widely linear estimation taking advantage of its geometric structure, and show that it can learn geometric transformations that the conventional neural networks cannot. First we formulate a fully augmented complex-valued neuron model based on the widely linear estimation. It is a generalized complex-valued neuron model that includes a usual complex-valued neuron and a degenerated case called a degenerated fully augmented complex-valued neuron. A fully augmented complex-valued neural network consists of such fully augmented complex-valued neurons. Secondly, we derive the back-propagation learning algorithms for the multi-layered fully augmented complex-valued neural networks. Finally, we find out via experiments that the multi-layered fully augmented complex-valued neural network has the different ability to learn 2D affine transformation from that of the usual complex-valued neural network.

show abstract

Complex-Valued Neural Networks: A Comprehensive Survey

Cited by 84 publications

References 191 publications

Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks

Impact of PolSAR Pre-Processing and Balancing Methods on Complex-Valued Neural Networks Segmentation Tasks

Maximum Lyapunov Exponent-based Multiple Chaotic Slime Mold Algorithm for Real-world Optimization

Proposal of fully augmented complex-valued neural networks

Contact Info

Product

Resources

About