|国家预印本平台
首页|Hybrid Real- and Complex-valued Neural Network Architecture

Hybrid Real- and Complex-valued Neural Network Architecture

Hybrid Real- and Complex-valued Neural Network Architecture

来源:Arxiv_logoArxiv
英文摘要

We propose a \emph{hybrid} real- and complex-valued \emph{neural network} (HNN) architecture, designed to combine the computational efficiency of real-valued processing with the ability to effectively handle complex-valued data. We illustrate the limitations of using real-valued neural networks (RVNNs) for inherently complex-valued problems by showing how it learnt to perform complex-valued convolution, but with notable inefficiencies stemming from its real-valued constraints. To create the HNN, we propose to use building blocks containing both real- and complex-valued paths, where information between domains is exchanged through domain conversion functions. We also introduce novel complex-valued activation functions, with higher generalisation and parameterisation efficiency. HNN-specific architecture search techniques are described to navigate the larger solution space. Experiments with the AudioMNIST dataset demonstrate that the HNN reduces cross-entropy loss and consumes less parameters compared to an RVNN for all considered cases. Such results highlight the potential for the use of partially complex-valued processing in neural networks and applications for HNNs in many signal processing domains.

Alex Young、Luan Vinícius Fiorio、Bo Yang、Boris Karanov、Wim van Houtum、Ronald M. Aarts

计算技术、计算机技术

Alex Young,Luan Vinícius Fiorio,Bo Yang,Boris Karanov,Wim van Houtum,Ronald M. Aarts.Hybrid Real- and Complex-valued Neural Network Architecture[EB/OL].(2025-04-04)[2025-07-01].https://arxiv.org/abs/2504.03497.点此复制

评论