Convolutional decoding using recurrent neural networks

Hamalainen, A.; Henriksson, J.

doi:10.1109/ijcnn.1999.836193

Cited by 20 publications

(6 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, it opened doors to different dimensions of collaboration Trosterud and Moshagen (2021), and even new ones beyond the original infrastructure itself, e.g., Snoek et al (2014), Simonenko, Alexandra (2020), Alnajja et al (2020). This also went beyond the principals foreseen by the originators Hämäläinen and Wiechetek (2020), Khanna et al (2021).…”

Section: Introductionmentioning

confidence: 99%

Establishing a Role for Minority Source Language in Multilingual Facilitation

Rueter

Partanen

Alnajjar

et al. 2022

NLY

View full text Add to dashboard Cite

This document is dedicated to a young man, who, despite the number of times he has traveled around the Sun, is always open to new thoughts on ways to include languages, especially the smaller ones, and the people who speak them in far-reaching and sustainable open-source de- velopment. Since Trond Trosterud in Tromsø is attributed a terrific track record in transnational and circum-polar linguistics, we try to attract his attention further afield, to languages and phe- nomena he has only touched. The language phenomena addressed here come from Erzya and the Zyrian variety of Komi; Erzya has issues presented but not discussed in his dissertation, whereas Komi brings in issues of adnominal and predicate number marking in conjunction with case homonymy that have been resolved thanks to the flexibility of the infrastructure.

show abstract

Section: Introductionmentioning

confidence: 99%

Establishing a Role for Minority Source Language in Multilingual Facilitation

Rueter

Partanen

Alnajjar

et al. 2022

NLY

View full text Add to dashboard Cite

show abstract

“…Accurate identification of sag sources and their fault phases is conducive to analyze, compensate and suppress local voltage sag. It can also be Convolutional Neural Networks (CNN) [28][29][30][31][32] contains two modules of feature extraction and classifier, in which the weights are updated continuously with the iterative process in training. The feature extraction neural network is mainly composed of multiple convolution layers and pooling layers.…”

Section: Introductionmentioning

confidence: 99%

Self-Supervised Voltage Sag Source Identification Method Based on CNN

Mei

Zhang

et al. 2019

Energies

View full text Add to dashboard Cite

A self-supervised voltage sag source identification method based on a convolution neural network is proposed in this study. In addition, a self-supervised CNN (Convolutional Neural Networks) voltage sag source identification model is constructed on the basis of the convolution neural network and AutoEncoder. The convolution layer and pool layer in CNN are used to extract the voltage sag characteristics, and the self-supervised network training process is realized based on the principle of AE. In the constructed mode, features which reflect the data characteristics are used rather than artificial features, thus improving the accuracy of practical application. It is unnecessary to input a lot of correct labels before the self-supervised training process. The model can meet the requirements of sag source identification on timeliness, practicability, diversity, and versatility in the context of modern big data. In this study, three-phase asymmetric sag sources in sag sources are classified into more detailed categories according to different fault phases. Therefore, the proposed method can not only identify the voltage sag source, but also accurately determine the specific fault phase. Finally, the optimal parameters of the model are recognized through a case study, and a self-supervised CNN model is established based on the data type of voltage sag. This model extracts features and identifies sag sources through the measured sag data. The superiority of the proposed method is verified by a comparison.

show abstract

“…As such, other candidate approaches must be studied. This work compares gradient adaptation, proposed originally in [22] for decoding and apparent also in [24], [25], as well as a modified form of belief propagation proposed in section 4.…”

Section: Introductionmentioning

confidence: 99%

Gradient Decoding Revisited

Regalia

2007

2007 Conference Record of the Forty-First Asilomar Conference on Signals, Systems and Computers

View full text Add to dashboard Cite

Modern coding applications, including dirty paper coding and information hiding, hinge critically on a classical 'general decoding problem,' known to be NP hard. Various attempts to find good solutions at reasonable complexity can be traced throughout the decades, most recently with attempts to achieve the rate-distortion bound in code word quantization. Here we take a step back to examine two computationally simple procedures in this direction: gradient decoding and a simple yet surprisingly effective variant on belief propagation that we dub truthiness propagation.

show abstract

Convolutional decoding using recurrent neural networks

Cited by 20 publications

References 5 publications

Establishing a Role for Minority Source Language in Multilingual Facilitation

Establishing a Role for Minority Source Language in Multilingual Facilitation

Self-Supervised Voltage Sag Source Identification Method Based on CNN

Gradient Decoding Revisited

Contact Info

Product

Resources

About