Noise Benefits in Complex-Valued Neural Networks

In this paper, we investigate the effectiveness of noise that is injected into the output of complex-valued neural networks. We first establish the equivalence between the complex backpropagation algorithm and the complex expectation maximization algorithm from the perspective of maximum probability...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2023 8th International Conference on Image, Vision and Computing (ICIVC) S. 853 - 858
Hauptverfasser: Ren, Lei, Liu, Chunyang, Zhang, Ying
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 27.07.2023
Schlagworte:
Backpropagation
Backpropagation algorithms
complex backpropagation algorithm
complex noisy expectation maximization algorithm
complex-valued neural networks
Estimation
Neural networks
Noise measurement
noise separation hyperplane
Numerical simulation
Training
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we investigate the effectiveness of noise that is injected into the output of complex-valued neural networks. We first establish the equivalence between the complex backpropagation algorithm and the complex expectation maximization algorithm from the perspective of maximum probability likelihood estimation, then based on this equivalence we establish the separation hyperplane to distinguish the beneficial noise from the harmful noise in the sense of speeding up the training. The theoretical findings are validated by numerical simulations on the MNIST and Fashion MNIST data sets.
DOI:10.1109/ICIVC58118.2023.10269993