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...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2023 8th International Conference on Image, Vision and Computing (ICIVC) s. 853 - 858
Hlavní autori: Ren, Lei, Liu, Chunyang, Zhang, Ying
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 27.07.2023
Predmet:
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
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí: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