# A mathematical motivation for complex-valued convolutional networks

arXiv: https://arxiv.org/abs/1503.03438 · HTML: https://mlsanity.com/paper/1503.03438/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2015.

## Built on by (most cited first, 13 of 13)

- [Deep Learning for Iris Recognition: A Survey](https://mlsanity.com/paper/2210.05866/) (2022)
- [Sum of Squares Circuits](https://mlsanity.com/paper/2408.11778/) (2024)
- [A Neural Network Warm-Start Approach for the Inverse Acoustic Obstacle Scattering Problem](https://mlsanity.com/paper/2212.08736/) (2022)
- [Towards Understanding Theoretical Advantages of Complex-Reaction Networks](https://mlsanity.com/paper/2108.06711/) (2021)
- [Phase Collapse in Neural Networks](https://mlsanity.com/paper/2110.05283/) (2021)
- [Adversarial Audio Synthesis with Complex-valued Polynomial Networks](https://mlsanity.com/paper/2206.06811/) (2022)
- [CoNO: Complex Neural Operator for Continous Dynamical Physical Systems](https://mlsanity.com/paper/2406.02597/) (2024)
- [Qualitative neural network approximation over R and C: Elementary proofs for analytic and polynomial activation](https://mlsanity.com/paper/2203.13410/) (2022)
- [On the Shift Invariance of Max Pooling Feature Maps in Convolutional Neural Networks](https://mlsanity.com/paper/2209.11740/) (2022)
- [Deep Learning-based MRI Reconstruction with Artificial Fourier Transform Network (AFTNet)](https://mlsanity.com/paper/2312.10892/) (2023)
- [Scaling Continuous Kernels with Sparse Fourier Domain Learning](https://mlsanity.com/paper/2409.09875/) (2024)
- [Epidemic Forecasting with a Hybrid Deep Learning Method Using CNN-LSTM With WOA-GWO Parameter Optimization: Global COVID-19 Case Study](https://mlsanity.com/paper/2503.12813/) (2025)
- [From CNNs to Shift-Invariant Twin Models Based on Complex Wavelets](https://mlsanity.com/paper/2212.00394/) (2022)

## Abstract (arXiv)

A complex-valued convolutional network (convnet) implements the repeated application of the following composition of three operations, recursively applying the composition to an input vector of nonnegative real numbers: (1) convolution with complex-valued vectors followed by (2) taking the absolute value of every entry of the resulting vectors followed by (3) local averaging. For processing real-valued random vectors, complex-valued convnets can be viewed as "data-driven multiscale windowed power spectra," "data-driven multiscale windowed absolute spectra," "data-driven multiwavelet absolute values," or (in their most general configuration) "data-driven nonlinear multiwavelet packets." Indeed, complex-valued convnets can calculate multiscale windowed spectra when the convnet filters are windowed complex-valued exponentials. Standard real-valued convnets, using rectified linear units (ReLUs), sigmoidal (for example, logistic or tanh) nonlinearities, max. pooling, etc., do not obviously exhibit the same exact correspondence with data-driven wavelets (whereas for complex-valued convnets, the correspondence is much more than just a vague analogy). Courtesy of the exact correspondence, the remarkably rich and rigorous body of mathematical analysis for wavelets applies directly to (complex-valued) convnets.