A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2011; you can also visit the original URL.
The file type is application/pdf.
Filters
Learning Signaling Network Structures with Sparsely Distributed Data
2009
Journal of Computational Biology
Preserved Fulltext
To address this problem, we present here an algorithm that enables structure learning for sparsely distributed data, allowing structure learning beyond the measurement technology's upper dimensionality ...
The single cell nature of the data ensures a very large dataset size, providing a statistically robust dataset for structure learning. ...
simultaneously, resulting in sparsely distributed data. ...
doi:10.1089/cmb.2008.07tt
pmid:19193145
pmcid:PMC3198894
fatcat:w3j3xv2o4ffijm7iwxpru3nr7u
Research on the Primary Features of the Internet of Things System and the Corresponding Data Communication Characteristics based on Sparse Coding and Joint Deep Neural Network
2016
International Journal of Future Generation Communication and Networking
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
With the advances of the deep neural network, we analyze the topology of the system network structure and extract the pattern features and characteristics to make the signal transmission process more quickly ...
To enhance the robustness and efficiency of the current IOT systems, we adopt the sparse coded dictionary learning theory to detect the size of the data and optimize the compressive sensing technique to ...
Deep learning research how to use multilayer structure automatic learning and potential distribution model data and it reduced the number of sample data and labeling requirements, through the training ...
doi:10.14257/ijfgcn.2016.9.10.11
fatcat:s65rrtxzqndwrlcvl35u5igix4
A Deep Neural Network Architecture Using Dimensionality Reduction with Sparse Matrices
[chapter]
2016
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Abstract We present a new deep neural network architecture, motivated by sparse random matrix theory that uses a low-complexity embedding through a sparse matrix instead of a conventional stacked autoencoder ...
We present a new deep neural network architecture, motivated by sparse random matrix theory that uses a low-complexity embedding through a sparse matrix instead of a conventional stacked autoencoder. ...
Section 4 concludes the document.
2 Deep neural network with sparse construction To establish notation, we first define a deep neural network structure. We use the N-dimensional vector = ! , ! ...
doi:10.1007/978-3-319-46681-1_48
fatcat:e3e7fkwkrvgadliavosmsazmka
Research on mechanical vibration monitoring based on wireless sensor network and sparse Bayes
2020
EURASIP Journal on Wireless Communications and Networking
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The traditional wired monitoring technology faces problems such as high-frequency signal pickup and high-precision data collection. ...
Therefore, this paper proposes optimization techniques for mechanical vibration monitoring and signal processing based on wireless sensor networks. ...
Comparison of sparse Bayesian learning and other algorithms In the previous chapter, in addition to introducing the concept of block sparse structure, several reconstruction algorithms using signal block ...
doi:10.1186/s13638-020-01836-9
fatcat:tjbcuqeg6za4ro5hprw6idaemq
Learning Structures for Deep Neural Networks
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Then as an implementation of the principle, we show that sparse coding can effectively maximize the entropy of the output signals, and accordingly design an algorithm based on global group sparse coding ...
neuroscience, to guide the procedure of structure learning without label information. ...
without fine-tuning; (3), initializing the network parameter with pre-trained dictionary and fine-tuned with BP; (4), restricting the network structure with learned mask and randomly initializing the ...
arXiv:2105.13905v1
fatcat:vfdwvno575ay7gpfv2u7phj3pm
Deep Learning Methods for Solving Linear Inverse Problems: Research Directions and Paradigms
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We review how deep learning methods are used in solving different linear inverse problems, and explore the structured neural network architectures that incorporate knowledge used in traditional methods ...
Nowadays, the rapid development of deep learning provides a fresh perspective for solving the linear inverse problem, which has various well-designed network architectures results in state-of-the-art performance ...
In [108], Zhang et al. construct their training data set with different noise distributions and train a single NN to deal with multiple noise distributions. ...
arXiv:2007.13290v2
fatcat:kqoerts77nftbl32fctx3za2me
End-to-End SAR Deep Learning Imaging Method Based on Sparse Optimization
2021
Remote Sensing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
soft threshold algorithm (ISTA) sparse algorithm in the two-dimensional data domain, and then reconstructs the observation scene through the superposition and expansion of the multi-layer network. ...
Based on the existing SAR sparse imaging algorithm, the SAR imaging model is first rewritten to the SAR complex signal form based on the real-value model. ...
Data Availability Statement: Not applicable.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/rs13214429
fatcat:6h2aury7j5h3vnl54qz4ym5xii
A Dictionary Learning Approach for Signal Sampling in Task-Based fMRI for Reduction of Big Data
2018
Frontiers in Neuroinformatics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is text/html.
In this paper, we present a structurally guided fMRI signal sampling method for dictionary learning and sparse representation of task fMRI data. ...
To address this problem, we propose a signal sampling approach for significant fMRI data reduction before performing structurally-guided dictionary learning and sparse coding of whole brain's fMRI data ...
doi:10.3389/fninf.2018.00017
pmid:29706880
pmcid:PMC5906552
fatcat:vivqlf3qcrdjde6ujo7hfq6e7m
Learned-SBL: A Deep Learning Architecture for Sparse Signal Recovery
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we present a computationally efficient sparse signal recovery scheme using Deep Neural Networks (DNN). ...
The architecture of the introduced neural network is inspired from sparse Bayesian learning (SBL) and named as Learned-SBL (L-SBL). ...
If the training data contains block sparse vectors, the L-SBL becomes a block sparse recovery algorithm. That is, L-SBL can learn any underlying structure in the training dataset. ...
arXiv:1909.08185v1
fatcat:ngeqfk464rct3eyuwo4b5cc47q
A Method of Rolling Bearing Fault Diagnose Based on Double Sparse Dictionary and Deep Belief Network
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Firstly, each type of fault signal is trained according to the double sparse dictionary learning algorithm and the corresponding double sparse subdictionaries is obtained. ...
A novel method based on the double sparse dictionary model joint with Deep Belief Network (DBN) is proposed for the fault diagnosis of rolling bearing. ...
of the original vibration signal under the double sparse dictionary is used as the data for deep neural network learning in proposed method. ...
doi:10.1109/access.2020.3003909
fatcat:syv3oz7q6jdhbi2aww6rsh63li
Power Quality Data Compression and Disturbances Recognition Based on Deep CS-BiLSTM Algorithm With Cloud-Edge Collaboration
2022
Frontiers in Energy Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
In terms of data transmission and feature extraction, the dictionary atoms and measurements uploaded at the edge are analyzed in the cloud by building a cloud-edge collaborative framework with distributed ...
Finally, the simulation analysis of 10 common power quality disturbance signals and 13 complex composite disturbance signals with random noise shows that the proposed method solves the problem of inadequate ...
AUTHOR CONTRIBUTIONS XX: Drafting the manuscript, CH: experimental analysis, HC: Review and Supervision, YL: Methodology and Formal analysis, BZ: Conceptualization and Revised, SW: Data Curation and Resources ...
doi:10.3389/fenrg.2022.874351
fatcat:eub5sunpnjgmdpnmpiant5eu2m
Channel Estimation for Massive MIMO Communication System Using Deep Neural Network
[article]
2018
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper we consider the problem of sparse signal recovery in Multiple Measurement Vectors (MMVs) case. ...
Afterwards, in order to reconstruct sparse vectors corresponding to this new set of equations, a four-layer feed-forward neural network is applied. ...
The proposed methods, by using deep neural network, learn the structure of sparse vectors and then, applying such learned networks, reconstruct the original sparse signals. ...
arXiv:1806.09126v1
fatcat:ufjb236msjealchbvvx5riqwve
Deep Feature Autoextraction Method for Intrapulse Data of Radar Emitter Signal
2021
Mobile Information Systems
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Concerned with the problems that the extracted features are the absence of objectivity for radar emitter signal intrapulse data because of relying on priori knowledge, a novel method is proposed. ...
Second, by optimizing the sparse autoencoder and confirming the training scheme, intrapulse deep features are autoextracted with encoder layer parameters. ...
When the intrapulse data are input into the network, the network will automatically learn to obtain the various levels of the input radar emitter signal, that means the feature expression. ...
doi:10.1155/2021/6870938
doaj:f0a99bb175644e41aa3257b7af60ab34
fatcat:vd4xfdq26rgl5lksg65nibideq
A Cloud Computing Fault Detection Method Based on Deep Learning
2017
Journal of Computer and Communications
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
Therefore, a fault detection method based on depth learning is proposed. An auto-encoder with sparse denoising is used to construct a parallel structure network. ...
It can automatically learn and extract the fault data characteristics and realize fault detection through deep learning. ...
In recent years, with the idea of deep learning, depth learning can use a large number of unlabeled data to achieve unsupervised automatic learning [13] , through data feature extraction, and then can ...
doi:10.4236/jcc.2017.512003
fatcat:uonygekeojdavn7lz2igrm5jym
Distributed Graph Learning with Smooth Data Priors
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
It also scales better in communication costs with the increase of the network size, especially for sparse networks. ...
Graph learning is generally performed centrally with a full knowledge of the graph signals, namely the data that lives on the graph nodes. ...
We also show that sparse networks
wireless sensor network, distributed optimization benefit more from a distributed solution than dense ones. ...
arXiv:2112.05887v1
fatcat:w2lkrp6nmzfkjodg3pujtpxviu
« Previous
Showing results 1 — 15 out of 85,308 results