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.
Filters
Performance Comparison between Pytorch and Mindspore
2022
International Journal of Database Management Systems
Preserved Fulltext
However, there is a large amount of data when training neural networks, which makes many deep learning frameworks appear to serve deep learning practitioners, providing services that are more convenient ...
To ensure that our survey is as comprehensive as possible, we carefully selected neural networks in 2 main domains, which cover computer vision and natural language processing (NLP). ...
ACKNOWLEDGEMENTS Supported by Beijing City University in 2021 "the innovation and entrepreneurship training program for college students" ...
doi:10.5121/ijdms.2022.14201
fatcat:vpq5wvjfnfbl7juh6i5572z6ze
Automatic Modulation Classification Based on Deep Learning for Software-Defined Radio
2020
Mathematical Problems in Engineering
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 introduced an improved deep neural architecture for implementing radio signal identification tasks, which is an important facet of constructing the spectrum-sensing capability required ...
The modules in the proposed architecture are repeated more times to increase the depth of neural network and the model's ability to learn features. ...
Deep Neural Network for Classification Modulation. Convolutional layers are a common element in all state-ofthe-art deep neural networks. ...
doi:10.1155/2020/2678310
fatcat:j76gojxdmjaq7jpz2boz4qwqki
Recognition of Handwritten Digit using Convolutional Neural Network in Python with Tensorflow and Comparison of Performance for Various Hidden Layers
[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 deep learning, Convolutional Neural Network (CNN) is at the center of spectacular advances that mixes Artificial Neural Network (ANN) and up to date deep learning strategies. ...
In recent times, with the increase of Artificial Neural Network (ANN), deep learning has brought a dramatic twist in the field of machine learning by making it more artificially intelligent. ...
In deep learning, Convolutional Neural Networking (CNN) [1, 2] is being used for visual imagery analyzing. ...
arXiv:1909.08490v1
fatcat:6wh2um4d4vc5vafce23763tdfm
JALAD: Joint Accuracy-And Latency-Aware Deep Structure Decoupling for Edge-Cloud Execution
2018
2018 IEEE 24th International Conference on Parallel and Distributed Systems (ICPADS)
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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2018 pre-print arXiv:1812.10027v1 fatcat:2umrsj2hgjaifih3bfg32bltbe
decoupling strategy to minimize the overall execution latency; and 3) An edge-cloud structure adaptation strategy that dynamically changes the decoupling for different network conditions. ...
A practical and critical problem thus has emerged: how to effectively deploy the deep neural network models such that they can be executed efficiently. ...
We observe that for these deep networks, c ≥ 4 already provides certain accuracy loss guarantee of 10%. ...
doi:10.1109/padsw.2018.8645013
dblp:conf/icpads/LiHJWWZ18
fatcat:m44nvmrc7neq5nl5lfmrzhvppe
Semi-supervised Deep Learning with Memory
[chapter]
2018
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.
In this work, we propose a novel Memory-Assisted Deep Neural Network (MA-DNN) capable of exploiting the memory of model learning to enable semi-supervised learning. ...
To address this problem, existing semi-supervised deep learning methods often rely on the up-to-date "network-in-training" to formulate the semi-supervised learning objective. ...
Semantics Limited, the Royal Society Newton Advanced Fellowship Programme (NA150459) and Innovate UK Industrial Challenge Project on Developing and Commercialising Intelligent Video Analytics Solutions for ...
doi:10.1007/978-3-030-01246-5_17
fatcat:xxd7ckagrfhtjdyvveqf4fabiu
Implementation of Fruits Recognition Classifier using Convolutional Neural Network Algorithm for Observation of Accuracies for Various Hidden Layers
[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
The overall performance losses of the network for different cases also observed. Finally, we have achieved the best test accuracy of 100% and a training accuracy of 99.79%. ...
Fruit recognition using Deep Convolutional Neural Network (CNN) is one of the most promising applications in computer vision. ...
Convolutional Neural Networks (CNNs) are classified as a deep learning algorithm. In deep learning, CNN [1, 2] are the most commonly used type of Artificial Neural Networks (ANNs). ...
arXiv:1904.00783v6
fatcat:vd7jasfcjndyrhlrjqm535h33i
Interpretable Machine Learning: Convolutional Neural Networks with RBF Fuzzy Logic Classification Rules
2018
2018 International Conference on Intelligent Systems (IS)
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.
This is achieved by creating a classification layer based on a Neural-Fuzzy classifier, and integrating it into the overall learning mechanism within the deep learning structure. ...
A convolutional neural network (CNN) learning structure is proposed, with added interpretability-oriented layers, in the form of Fuzzy Logic-based rules. ...
He et al. provided a model structure to build deep neural networks without considerable gradient loss [10] . ...
doi:10.1109/is.2018.8710470
dblp:conf/is/XiP18
fatcat:kz45t3h4azfufb6cd6zbhs4cya
Incorporating Uncertainty in Learning to Defer Algorithms for Safe Computer-Aided Diagnosis
[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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2108.07392v4 fatcat:aneggogzcjc6bdfcpzdi4n3mamOther Versions
Deep neural networks are increasingly being used for computer-aided diagnosis, but erroneous diagnoses can be extremely costly for patients. ...
Importantly, the weight of the defer loss in LDU can be easily adjusted to obtain the desired trade-off between diagnostic accuracy and deferral rate. ...
Deep ensembles, i.e. ensembles of deep neural networks trained with different random initializations [9] , have been found sufficient for capturing epistemic uncertainty, without the need for additional ...
arXiv:2108.07392v5
fatcat:ksmpfh3b6zgb7nbp6a4hepc3ya
Video retrieval based on deep convolutional neural network
[article]
2017
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, a deep convolutional neural network is proposed to extract high-level semantic features and a binary hash function is then integrated into this framework to achieve an end-to-end optimization ...
Particularly, our approach also combines triplet loss function which preserves the relative similarity and difference of videos and classification loss function as the optimization objective. ...
Finally, we update the parameters of the network by minimizing the overall loss function. ...
arXiv:1712.00133v1
fatcat:zf2lnzivcffmbkg3cwztqvypjy
A Deep Convolutional Neural Network for Lung Cancer Diagnostic
[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 2020; you can also visit the original URL.
The file type is application/pdf.
We aim to learn discriminant compact features at beginning of our deep convolutional neural network. ...
In this paper, we examine the strength of deep learning technique for diagnosing lung cancer on medical image analysis problem. ...
To address this issue, we propose a new deep convolutional neural network (dCNN) architecture. ...
arXiv:1804.08170v1
fatcat:z5w7begvyjb4rek43xmbqebvkq
Using deep neural networks for radiogenomic analysis
2018
2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
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.
A deep autoencoder was trained on 528 patients, each with 12,042 gene expressions. Then, the autoencoder's weights were used to initialize a supervised deep neural network. ...
We found that neural network pre-trained with an autoencoder and dropout had lower errors than linear regression in predicting tumor morphology features by an average of 16.98% mean absolute percent error ...
Similarly, the mean training and validation losses were 0.021 and 0.143 for the neural network without pre-training and 0.022 and 0.146 for the neural network with pretraining. ...
doi:10.1109/isbi.2018.8363864
pmid:30093961
pmcid:PMC6081189
dblp:conf/isbi/SmedleyH18
fatcat:gxliyck2ibh4th2khpauspqste
Detection of Aerobics Action Based on Convolutional Neural Network
2022
Computational Intelligence and Neuroscience
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.
The results show that the loss function of the neural network is reduced to 0.2 by using the proposed method, and the accuracy of the proposed method can reach 96.5% compared with other methods, which ...
So, the low-level semantic information in the images can be extracted, and it can be converted into high-resolution deep-level semantic information. ...
It can be seen that the ability of the target detection network to detect human targets is gradually fitted to the datasets used for training. e trend of overall loss function values of the entire neural ...
doi:10.1155/2022/1857406
pmid:35035453
pmcid:PMC8754619
fatcat:txs5hjhuwncupj6jvssj2h2r7m
Deep Multi-Layer Perception Based Terrain Classification for Planetary Exploration Rovers
2019
Sensors
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.
Secondly, a deep neural network based on multi-layer perception is designed to realize classification of different terrains. ...
Accurate classification and identification of the detected terrain is the basis for the long-distance patrol mission of the planetary rover. ...
for deep network training. ...
doi:10.3390/s19143102
fatcat:vu6o3lbotfbgfnpfazwsveliky
PrimeNet: Adaptive Multi-Layer Deep Neural Structure for Enhanced Feature Selection in Early Convolution Stage
2022
Applied Sciences
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.
for parallel and multilayer deep neural systems. ...
The colossal depths of the deep neural network sometimes suffer from ineffective backpropagation of the gradients through all its depths, whereas the strong performance of shallower multilayer neural structures ...
Acknowledgments: We wish to acknowledge the tremendous support from Department of Computer and Information Sciences (CISD), UTP, Malaysia for all academic support and facilities. ...
doi:10.3390/app12041842
fatcat:2nlvg77znrhq7hcjikjis3bjuu
A Deep Residual U-Type Network for Semantic Segmentation of Orchard Environments
2020
Applied Sciences
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.
Finally, a network was built through the Pytorch Deep Learning Framework, which was implemented to train the data set and compare the network with the fully convolutional neural network, the U-type network ...
The results show that the deep residual U-type network has the highest recognition accuracy, with an average of 85.95%, making it more suitable for environment recognition in orchards. ...
(Chengdu, Sichuan, China), for kindly providing valuable suggestions and help.
Conflicts of Interest: The authors declare no conflict of interest. ...
doi:10.3390/app11010322
fatcat:pd45a2berrdvvkscmm2zjphwce
« Previous
Showing results 1 — 15 out of 145,482 results