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.
Filters
Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery
[article]
2018
arXiv
pre-print
Preserved Fulltext
Besides memory demands, learning dynamics like vanishing gradients and slow convergence due to infrequent weight updates can reduce BPTT's practicality; meanwhile, although online recurrent network learning ...
This is especially true during the initial learning stages, when exploratory behaviour can increase the delay between specific actions and their effects. ...
LSTM and GRU architectures introduce gating mechanisms to mitigate vanishing gradients, and constraining recurrent network weights can also help. ...
arXiv:1805.04955v1
fatcat:wd2gnhpuxjckvexvwl3yzz3pnm
Application of deep learning algorithms and architectures in the new generation of mobile networks
2021
Serbian Journal of Electrical 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 2022; you can also visit the original URL.
The file type is application/pdf.
Finally, the paper presents practical use case of modulation classification as implementation of deep learning in an application essential for modern spectrum management. ...
Having firstly presented the background of deep learning and related technologies, the paper goes on to present the architectures used for deployment of deep learning in mobile networks. ...
In [18] the authors proposed networks with Gated Recurrent Units (GRUs), representing, roughly speaking, light and trimmed LSTM alternative, showing that complex architecture of LSTMs may not be necessary ...
doi:10.2298/sjee2103397d
fatcat:n3hduljspfbt3mkq2zdzbae72u
RMDL
2018
Proceedings of the 2nd International Conference on Information System and Data Mining - ICISDM '18
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:1805.01890v1 fatcat:l6efrredpvgqplro5zrbgtz6yuOther Versions
This paper introduces Random Multimodel Deep Learning (RMDL): a new ensemble, deep learning approach for classification. ...
This paper describes RMDL and shows test results for image and text data including MNIST, CIFAR-10, WOS, Reuters, IMDB, and 20newsgroup. ...
RMDL uses two specific RNN structures: Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM). ...
doi:10.1145/3206098.3206111
dblp:conf/icisdm/KowsariHBMB18
fatcat:lzyx7ze67vgu5lv2jbguion544
Recent Advances in Recurrent Neural Networks
[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.
Other Versions
Recurrent neural networks (RNNs) are capable of learning features and long term dependencies from sequential and time-series data. ...
A well-trained RNN can model any dynamical system; however, training RNNs is mostly plagued by issues in learning long-term dependencies. ...
In [94] , RCNNs are used for text classification on several datasets. ...
arXiv:1801.01078v3
fatcat:ioxziqbkmzdrfoh2kukul6xlku
Long-Term Recurrent Convolutional Networks for Visual Recognition and Description
2017
IEEE Transactions on Pattern Analysis and Machine Intelligence
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 2015; you can also visit the original URL.
The file type is application/pdf.
We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition ...
Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics ...
This work was supported in part by DARPA's MSEE and SMISC programs, NSF awards IIS-1427425, and IIS-1212798, IIS-1116411, Toyota, and the Berkeley Vision and Learning Center. ...
doi:10.1109/tpami.2016.2599174
pmid:27608449
fatcat:xoluu2wo6jfbxddalikzfbrgk4
Long-term recurrent convolutional networks for visual recognition and description
2015
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
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 2015; you can also visit the original URL.
The file type is application/pdf.
We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition ...
Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics ...
This work was supported in part by DARPA's MSEE and SMISC programs, NSF awards IIS-1427425, and IIS-1212798, IIS-1116411, Toyota, and the Berkeley Vision and Learning Center. ...
doi:10.1109/cvpr.2015.7298878
dblp:conf/cvpr/DonahueHGRVDS15
fatcat:5w4eeyesm5hipiieav2nzc4et4
DeepFuseOSV: online signature verification using hybrid feature fusion and depthwise separable convolution neural network architecture
2020
IET Biometrics
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.
DWSCNN is utilised for extracting deep feature representations and LSTM is competent in learning long term dependencies of stroke points of a signature. ...
(ii) a hybrid architecture combining depth-wise separable convolution neural network (DWSCNN) and long short term memory (LSTM) network delivering state-of-the-art performance for OSV is proposed. ...
[21] structured a novel semisupervised system for assessing the signature complexity utilising recurrent neural networks (RNNs). ...
doi:10.1049/iet-bmt.2020.0032
fatcat:vhhcmpakz5c4di3o7tbkfcaqsa
On Architectures for Including Visual Information in Neural Language Models for Image Description
[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.
We also observe that the merge architecture can have its recurrent neural network pre-trained in a text-only language model (transfer learning) rather than be initialised randomly as usual. ...
Our work opens up new avenues of research in neural architectures, explainable AI, and transfer learning. ...
compared architectures with simple RNNs and LSTMs. ...
arXiv:1911.03738v1
fatcat:ncbx3ee22nhmfjh4u6mierrrbu
Systematic reviews in sentiment analysis: a tertiary study
2021
Artificial Intelligence Review
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.
According to this analysis, LSTM and CNN algorithms are the most used deep learning algorithms for sentiment analysis. ...
In addition to the tertiary study, we also identified recent 112 deep learning-based sentiment analysis papers and categorized them based on the applied deep learning algorithms. ...
The advantages of Recurrent Neural Networks are their simple architectures and their ability to learn tree structures. ...
doi:10.1007/s10462-021-09973-3
fatcat:zo7igc4fnnh47kyafncbfmaf3u
RC-RNN: Reconfigurable Cache Architecture for Storage Systems Using Recurrent Neural Networks
2021
IEEE Transactions on Emerging Topics in Computing
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:2111.03297v1 fatcat:bqibbxtpabgzbgnt4t6opvbxpy
In this paper, we propose RC-RNN, the first reconfigurable SSD-based cache architecture for storage systems that utilizes machine learning to identify performance-critical data pages for I/O caching. ...
The proposed architecture uses Recurrent Neural Networks (RNN) to characterize ongoing workloads and optimize itself towards higher cache performance while improving SSD lifetime. ...
We utilize Recurrent Neural Network (RNN) in the proposed architecture as one of the most powerful machine learning methods, which is proven to be accurate in several application domains such as text analysis ...
doi:10.1109/tetc.2021.3102041
fatcat:gyqnb3526fbebohwr4qapeiche
Hybrid deep neural network for Bangla automated image descriptor
2020
IJAIN (International Journal of Advances in Intelligent Informatics)
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 model employs Convolutional Neural Network (CNN) to classify the whole dataset, while Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) capture the sequential semantic representation ...
In this study, a novel dataset was constructed by generating Bangla textual descriptor from visual input, called Bangla Natural Language Image to Text (BNLIT), incorporating 100 classes with annotation ...
Acknowledgment The authors are thankful to the Department of Computer Science and Engineering at the University of Liberal Arts Bangladesh for their research lab and other crucial technical support along ...
doi:10.26555/ijain.v6i2.499
fatcat:5wamb5fycjgtvai3dqhd33yq3a
Online handwritten Gurmukhi word recognition using fine-tuned Deep Convolutional Neural Network on offline features
2021
Machine Learning with Applications
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.
The present study provided benchmark results for online handwritten Gurmukhi word recognition using deep learning architecture convolutional neural network, and obtained above 97% recognition accuracy ...
Experimental results demonstrated that the deep learning system achieved great results in Gurmukhi script and outperforms existing results in the literature. ...
These controlled states are referred as gated memory/state, and these are part of LSTMs and gated recurrent units. ...
doi:10.1016/j.mlwa.2021.100037
fatcat:ohu2dktiifft3lyecf6g3yuauu
CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope
2021
Electronics
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.
Several inspirational concepts for the progress of CNN have been investigated, including alternative activation functions, regularization, parameter optimization, and architectural advances. ...
Furthermore, the introduction of large amounts of data and readily available hardware has opened new avenues for CNN study. ...
Acknowledgments: The authors would like to thank the reviewers for their valuable suggestions which helped in improving the quality of this paper. ...
doi:10.3390/electronics10202470
fatcat:aqhrysjtbjagzl6byalgy2du5a
Framework for Deep Learning-Based Language Models using Multi-task Learning in Natural Language Understanding: A Systematic Literature Review and Future Directions
2022
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 2022; you can also visit the original URL.
The file type is application/pdf.
NLU (Natural Language Understanding) is a subset of NLP including tasks, like machine translation, dialogue-based systems, natural language inference, text entailment, sentiment analysis, etc. ...
INDEX TERMS Deep learning, Knowledge representation, Multi-task NLU, Unsupervised learning TABLE I APPLICATION DOMAINS FOR NLU Domain Applications Machine translation IBM Watson Task-based dialogue-based ...
MT-LSTM is reported to beat a collection of baselines, including LSTM and RNN-based text categorization models. ...
doi:10.1109/access.2022.3149798
fatcat:k3kdt4eryzdfpk5k6w62jtlskm
A tutorial survey of architectures, algorithms, and applications for deep learning
2014
APSIPA Transactions on Signal and Information Processing
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.
classification and for feature learning. ...
Three representative deep architectures -deep autoencoders, deep stacking networks with their generalization to the temporal domain (recurrent networks), and deep neural networks (pretrained with deep ...
Although such more complex architectures have produced state of the a tutorial survey of architectures, algorithms, and applications for deep learning art results (e.g., [154] ), their complexity does ...
doi:10.1017/atsip.2013.9
fatcat:4l4uonhhcffkbfot2fztpfxo2e
« Previous
Showing results 1 — 15 out of 830 results