Papers › Trainable Fractional Fourier Transform

Trainable Fractional Fourier Transform

4 Mar 2024IEEE Signal Processing Letters 2024 3archive 2025-07-28

Emirhan Koç, Tuna Alikaşifoğlu, Arda Can Aras, Aykut Koç

Recently, the fractional Fourier transform (FrFT) has been integrated into distinct deep neural network (DNN) models such as transformers, sequence models, and convolutional neural networks (CNNs). In these studies, the fraction order is considered a hyperparameter and tuned manually to find the suitable values. By taking these one step further, we extend the scope of FrFT and introduce it as a trainable layer in various neural network architectures, where the fraction order is learned in the training stage along with the network weights. First, we mathematically show that fraction order can be updated through backpropagation in the network training phase. To support this formulation, we conduct extensive experiments encompassing image classification and time series prediction tasks on benchmark datasets. Our results show that the trainable FrFT layers alleviate the need to search for suitable fraction orders and improve performance over time and Fourier domain approaches.

PaperPDFCode

Code

tunakasif/torch-frft officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image ClassificationTime SeriesTime Series Predictionimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections