Filters








4,888 Hits in 6.9 sec

Drug Discovery Approaches using Quantum Machine Learning [article]

Junde Li, Mahabubul Alam, Congzhou M Sha, Jian Wang, Nikolay V. Dokholyan, Swaroop Ghosh
<span title="2021-04-01">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Classical machines cannot efficiently produce atypical patterns of quantum computers which might improve the training quality of learning tasks.  ...  We propose a suite of quantum machine learning techniques e.g., generative adversarial network (GAN), convolutional neural network (CNN) and variational auto-encoder (VAE) to generate small drug molecules  ...  Note that, (iii) has trainable parameters in the CNN layer which are learned during the training alongside the trainable parameters in the MLP.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.00746v1">arXiv:2104.00746v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cakmo32dzvdazaziszhgvquory">fatcat:cakmo32dzvdazaziszhgvquory</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210406001716/https://arxiv.org/pdf/2104.00746v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/93/05/93055e2e0771d3a907d2c5455c7d5208f63ebc9c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.00746v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

An Efficient and Accurate Depth-Wise Separable Convolutional Neural Network for Cybersecurity Vulnerability Assessment Based on CAPTCHA Breaking

Stephen Dankwa, Lu Yang
<span title="2021-02-18">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ikdpfme5h5egvnwtvvtjrnntyy" style="color: black;">Electronics</a> </i> &nbsp;
In this study, in contrast to breaking the whole CAPTCHA images simultaneously, this study split four-character CAPTCHA images for the individual characters with a 2-pixel margin around the edges of a  ...  new training dataset, and then proposed an efficient and accurate Depth-wise Separable Convolutional Neural Network for breaking text-based CAPTCHAs.  ...  We express our sincere thanks to the graduate school of University of Electronic Science and Technology of China for providing us the experimental resources.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10040480">doi:10.3390/electronics10040480</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l6aapljfbzcbtjykq4dwbjc2qq">fatcat:l6aapljfbzcbtjykq4dwbjc2qq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210306081619/https://res.mdpi.com/d_attachment/electronics/electronics-10-00480/article_deploy/electronics-10-00480-v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e9/9e/e99e27f461f560b08e123c0f845d9bbe20ccf03e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10040480"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Coal/Gangue Recognition Using Convolutional Neural Networks and Thermal Images

Murad S Alfarzaeai, Niu Qiang, Jiaqi Zhao, Refat M A Eshaq, Eryi Hu
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
This paper addressed the topic of Coal/Gangue recognition and built a new model called (CGR-CNN) based on Convolutional Neural network (CNN) and using thermal images as standard images for Coal/Gangue  ...  ) validation accuracy, in the prediction phase (160) new images of coal and gangue (80 for both) have been tested to measure the efficiency of the work, the prediction result comes with (100%) for coal  ...  layer giving (102,500) training parameters with Relu activation function, finally the last fully connected layer comes with softmax activation function at the end with (2) classes to represent the coal  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2990200">doi:10.1109/access.2020.2990200</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7fuv2yqtx5g2hlpzfnfwlelvka">fatcat:7fuv2yqtx5g2hlpzfnfwlelvka</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108194020/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09078124.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f6/2f/f62f4079df2738fea5597854db318f5f2ee7711b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2990200"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

An Attention-Based Hybrid Network for Automatic Detection of Alzheimer's Disease from Narrative Speech

Jun Chen, Ji Zhu, Jieping Ye
<span title="2019-09-15">2019</span> <i title="ISCA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/trpytsxgozamtbp7emuvz2ypra" style="color: black;">Interspeech 2019</a> </i> &nbsp;
The proposed network is based on attention mechanism and is composed of a CNN and a GRU module.  ...  Alzheimer's disease (AD) is one of the leading causes of death in the world and affects at least 50 million individuals. Currently, there is no cure for the disease.  ...  MCI is the intermediate stage between normal aging and AD, and is regarded as a suitable stage for early intervention and potential treatment.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2019-2872">doi:10.21437/interspeech.2019-2872</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/interspeech/ChenZY19.html">dblp:conf/interspeech/ChenZY19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vatlpkwsf5hofdk2adgwuprxqa">fatcat:vatlpkwsf5hofdk2adgwuprxqa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211208144652/https://www.isca-speech.org/archive/pdfs/interspeech_2019/chen19n_interspeech.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/4e/41/4e4136382ddab4b5b357dd8c9c81789d930065fb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.21437/interspeech.2019-2872"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

FPETS : Fully Parallel End-to-End Text-to-Speech System [article]

Dabiao Ma, Zhiba Su, Wenxuan Wang, Yuhao Lu
<span title="2020-02-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Different from RNN, UFANS can capture long term information in a fully parallel manner. Trainable position encoding and two-step training strategy are used for learning better alignments.  ...  Experimental results show FPETS utilizes the power of parallel computation and reaches a significant speed up of inference compared with state-of-the-art end-to-end TTS systems.  ...  In order to train a better alignment model, we propose a two-stage training strategy. Our model focus more on alignment learning in stage 1.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.05710v5">arXiv:1812.05710v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/htdku4cd3bhorpbhmx3onjyqym">fatcat:htdku4cd3bhorpbhmx3onjyqym</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321061008/https://arxiv.org/pdf/1812.05710v5.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.05710v5" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

FPETS: Fully Parallel End-to-End Text-to-Speech System

Dabiao Ma, Zhiba Su, Wenxuan Wang, Yuhao Lu
<span title="2020-04-03">2020</span> <i title="Association for the Advancement of Artificial Intelligence (AAAI)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wtjcymhabjantmdtuptkk62mlq" style="color: black;">PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE</a> </i> &nbsp;
Different from RNN, UFANS can capture long term information in a fully parallel manner. Trainable position encoding and two-step training strategy are used for learning better alignments.  ...  Experimental results show FPETS utilizes the power of parallel computation and reaches a significant speed up of inference compared with state-of-the-art end-to-end TTS systems.  ...  In order to train a better alignment model, we propose a two-stage training strategy. Our model focus more on alignment learning in stage 1.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i05.6365">doi:10.1609/aaai.v34i05.6365</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4ahzna6eqfbkpej5g4ejops4re">fatcat:4ahzna6eqfbkpej5g4ejops4re</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103171817/https://aaai.org/ojs/index.php/AAAI/article/download/6365/6221" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/af/8e/af8e7b2af0700a235293942802ba1b2bfb178ec8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1609/aaai.v34i05.6365"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Target Aware Network Architecture Search and Compression for Efficient Knowledge Transfer [article]

S.H.Shabbeer Basha, Debapriya Tula, Sravan Kumar Vinakota, Shiv Ram Dubey
<span title="2022-05-12">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This two-stage mechanism finds a compact version of the pre-trained CNN with optimal structure (number of filters in a convolutional layer, number of neurons in a dense layer, and so on) from the hypothesis  ...  To tackle this problem, we propose a two-stage framework called TASCNet which enables efficient knowledge transfer.  ...  The key contributions of this research are as follows, • A novel two-stage framework is developed for reducing the capacity of a pre-trained CNN for the target task. • The hyperparameters of layers of  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.05967v1">arXiv:2205.05967v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hml3fanawzffropbbtpzcwhhii">fatcat:hml3fanawzffropbbtpzcwhhii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220516013313/https://arxiv.org/pdf/2205.05967v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/5c/ac/5cac654c27496e9b1353c54b3f9506483395ea5a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.05967v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Top-down Attention Recurrent VLAD Encoding for Action Recognition in Videos [article]

Swathikiran Sudhakaran, Oswald Lanz
<span title="2018-08-29">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We adopt a top-down approach of attention, by using class specific activation maps obtained from a deep CNN pre-trained for image classification, to weight appearance features before encoding them into  ...  Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification.  ...  The network is trained for 50 epochs in stage 1 with a learning rate of 10 −2 and 30 epochs in stage 2 with a learning rate of 10 −4 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.09892v1">arXiv:1808.09892v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jcxyvdlc4jcf5iquu4z4bzbyqu">fatcat:jcxyvdlc4jcf5iquu4z4bzbyqu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826023651/https://arxiv.org/pdf/1808.09892v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b1/d2/b1d2001e877bb36c8ccc97bee62d9824a3b8874d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1808.09892v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Exploring Font-independent Features for Scene Text Recognition [article]

Yizhi Wang, Zhouhui Lian
<span title="2020-09-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Specifically, we introduce trainable font embeddings to shape the font styles of generated glyphs, with the image feature of scene text only representing its essential patterns.  ...  The generation process is directed by the spatial attention mechanism, which effectively copes with irregular texts and generates higher-quality glyphs than existing image-to-image translation methods.  ...  The Glyph Discriminator is a lightweight CNN followed by a fully connected layer with sigmoid activation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.07447v1">arXiv:2009.07447v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uiql56bx6bdippff3axacpxyru">fatcat:uiql56bx6bdippff3axacpxyru</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930021426/https://arxiv.org/pdf/2009.07447v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.07447v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Energy-Efficient Gabor Kernels in Neural Networks with Genetic Algorithm Training Method

Fanjie Meng, Xinqing Wang, Faming Shao, Dong Wang, Xia Hua
<span title="2019-01-18">2019</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ikdpfme5h5egvnwtvvtjrnntyy" style="color: black;">Electronics</a> </i> &nbsp;
In addition, we propose a procedure to train Gabor CNNs, termed the fast training method (FTM).  ...  The experimental result of the Gabor CNN and MPGA training method shows a 17–19% reduction in computational energy and time and an 18–21% reduction in storage requirements with a less than 1% accuracy  ...  Author Contributions: F.M. and X.W. were responsible for the overall work and proposed the idea and experiments of the method in the paper, and the paper was written mainly by the two authors.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics8010105">doi:10.3390/electronics8010105</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zsmrzk4iznb5zfbbr3ryqhmh4i">fatcat:zsmrzk4iznb5zfbbr3ryqhmh4i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190504040829/https://res.mdpi.com/electronics/electronics-08-00105/article_deploy/electronics-08-00105.pdf?filename=&amp;attachment=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ed/7c/ed7c2f247075bb07019e4279dbc3ae0a3f3629b7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics8010105"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

DualNet: Locate Then Detect Effective Payload with Deep Attention Network [article]

Shiyi Yang, Peilun Wu, Hui Guo
<span title="2020-10-23">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To address the above problems, in this paper, we propose a novel neural network based detection system, DualNet, which is constructed with a general feature extraction stage and a crucial feature learning  ...  We evaluate the DualNet on two benchmark cyber attack datasets, NSL-KDD and UNSW-NB15.  ...  The Dual-Net mainly performs two stages for attack recognition. The construction of two stages is elaborated in the next two sub sections. A.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.12171v1">arXiv:2010.12171v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6fti4qa5i5eanpwke4sxyvqsre">fatcat:6fti4qa5i5eanpwke4sxyvqsre</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201029061717/https://arxiv.org/pdf/2010.12171v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9d/ab/9dab733c3e30d01ca3b7545d17bc25a08ae43b65.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.12171v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

End-to-End Video Captioning [article]

Silvio Olivastri, Gurkirt Singh, Fabio Cuzzolin
<span title="2019-11-08">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In a two-stage training setting, we first initialise our architecture using pre-trained encoders and decoders -- then, the entire network is trained end-to-end in a fine-tuning stage to learn the most  ...  The (video) encoder is traditionally a Convolutional Neural Network (CNN), while the decoding (for language generation) is done using a Recurrent Neural Network (RNN).  ...  ), (5) where σ is a sigmoid activation function.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.02628v2">arXiv:1904.02628v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/s4akev34t5aevnniq26hydqln4">fatcat:s4akev34t5aevnniq26hydqln4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200912174604/https://arxiv.org/pdf/1904.02628v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/19/27/19274880ae189722e39ee560ebb557395207c743.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.02628v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Hybrid Deep Model for Recognizing Arabic Handwritten Characters

Naseem Alrobah, Saleh Albahli
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Acknowledgment: We would like to thank the Deanship of Scientific Research, Qassim University for funding the publication of this project.  ...  This section illustrates the enhanced two-stage training procedure of the hybrid CNN models. • First Stage (training the CNN with backpropagation): the convolutional layers in CNN learn their weights during  ...  These blocks are followed by 5 FCL with ReLU activation function. The original output layer of the model is an FCL with 115 neurons, and softmax is used as an activation function.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3087647">doi:10.1109/access.2021.3087647</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2ynacbcp35f4zdx5u6rwdp2esy">fatcat:2ynacbcp35f4zdx5u6rwdp2esy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210612092950/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09448231.pdf?tp=&amp;arnumber=9448231&amp;isnumber=6514899&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/90/7e/907ecf3119c96ddd6680358bfe256a6a3cdc3d08.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3087647"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Light-Weighted CNN for Text Classification [article]

Ritu Yadav
<span title="2020-04-16">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
With the help of this architecture, we can achieve a drastic reduction in trainable parameters.  ...  For management, documents are categorized into a specific category, and to do these, most of the organizations use manual labor.  ...  Also, softmax-cross entropy for loss and RELU activation function is used for adding non-linearity to the network.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.07922v1">arXiv:2004.07922v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t376rmp4kzbynauictiwcrazim">fatcat:t376rmp4kzbynauictiwcrazim</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200507042541/https://arxiv.org/pdf/2004.07922v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.07922v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

CME Arrival Time Prediction Using Convolutional Neural Network

Yimin Wang, Jiajia Liu, Ye Jiang, Robert Erdélyi
<span title="2019-08-07">2019</span> <i title="American Astronomical Society"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/otgg2yqymve23nrsflax26msgm" style="color: black;">Astrophysical Journal</a> </i> &nbsp;
Unlike previous studies on this topic, our proposed CNN regression model does not require manually selected features for model training, does not need time spent on feature collection, and can deliver  ...  In this paper, we use a deep learning framework, i.e. a convolutional neural network (CNN) regression model, to analyze transit times from the Sun to the Earth of 223 geo-effective CME events observed  ...  A BN computes two trainable parameters and two non-trainable parameters per feature map on the previous layer, which makes the BN in the first layer having 4 × 64 = 256 parameters with 128 trainable and  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3847/1538-4357/ab2b3e">doi:10.3847/1538-4357/ab2b3e</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hrhfytlbs5govdclsiftg5rmne">fatcat:hrhfytlbs5govdclsiftg5rmne</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200305175251/http://eprints.whiterose.ac.uk/149545/1/72157_3_art_file_4003567_prhpm6.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3f/d1/3fd1524dde2ff66d075693dc2520151a46942576.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3847/1538-4357/ab2b3e"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 4,888 results