# A Hybrid Complex-valued Neural Network Framework with Applications to Electroencephalogram (EEG)

arXiv: https://arxiv.org/abs/2207.14799 · HTML: https://mlsanity.com/paper/2207.14799/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 58 references that are in the map.
- First posted on arXiv 28 Jul 2022.

## Builds on (most cited first, 7 of 7)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep Complex Networks](https://mlsanity.com/paper/1705.09792/) (2017)
- [A Survey of Complex-Valued Neural Networks](https://mlsanity.com/paper/2101.12249/) (2021)
- [On Complex Valued Convolutional Neural Networks](https://mlsanity.com/paper/1602.09046/) (2016)
- [EEG-based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies on Signal Sensing Technologies and Computational Intelligence Approaches and their Applications](https://mlsanity.com/paper/2001.11337/) (2020)
- [Complex-valued Neural Networks with Non-parametric Activation Functions](https://mlsanity.com/paper/1802.08026/) (2018)
- [Compact Convolutional Neural Networks for Classification of Asynchronous Steady-state Visual Evoked Potentials](https://mlsanity.com/paper/1803.04566/) (2018)

## Built on by (most cited first, 2 of 2)

- [Efficient and Interpretable Neural Networks Using Complex Lehmer Transform](https://mlsanity.com/paper/2501.15223/) (2025)
- [Hybrid Real- and Complex-valued Neural Network Architecture](https://mlsanity.com/paper/2504.03497/) (2025)

## Abstract (arXiv)

In this article, we present a new EEG signal classification framework by integrating the complex-valued and real-valued Convolutional Neural Network(CNN) with discrete Fourier transform (DFT). The proposed neural network architecture consists of one complex-valued convolutional layer, two real-valued convolutional layers, and three fully connected layers. Our method can efficiently utilize the phase information contained in the DFT. We validate our approach using two simulated EEG signals and a benchmark data set and compare it with two widely used frameworks. Our method drastically reduces the number of parameters used and improves accuracy when compared with the existing methods in classifying benchmark data sets, and significantly improves performance in classifying simulated EEG signals.