Work

Incommensurate fractional recurrent neural networks

Year: 2025

Type: article

Abstract: This paper introduces a novel class of neural networks called Incommensurate Fractional Recurrent Neural Networks (FRNNs) , inspired by incommensurate fractional difference systems. Unlike classical RNNs, FRNNs incorporate learnable fractional orders to capture heterogeneous temporal dependencies. To address the failure of back-propagation caused by cross-layer and cross-time coupling, we propose a forward-forward recursive gradient computation method combined with mini-batch SGD and ADAM optimization. Extensive experiments on multiple time-series datasets, including synthetic sinusoidal sequences, chaotic sequences, and real-world financial and energy data, demonstrate that FRNN achieves lower prediction error compared to RNN. These results confirm the effectiveness of fractional memory dynamics for sequential data processing.

Source: Neurocomputing

DOI: 10.1016/j.neucom.2025.132535

Authors: Babak Shiri, Zahra Alijani, Ioannis Dassios, Dumitru Baleanu

Institutions: Neijiang Normal University, University of Ostrava, Aristotle University of Thessaloniki, Institute of Space Science - INFLPR Subsidiary, Lebanese American University

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $2,670

Funder: European Commission