Filters








16,338 Hits in 5.1 sec

Robust Processing-In-Memory Neural Networks via Noise-Aware Normalization [article]

Li-Huang Tsai, Shih-Chieh Chang, Yu-Ting Chen, Jia-Yu Pan, Wei Wei, Da-Cheng Juan
<span title="2020-11-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, PIM accelerators often suffer from intrinsic noise in the physical components, making it challenging for neural network models to achieve the same performance as on the digital hardware.  ...  Analog computing hardwares, such as Processing-in-memory (PIM) accelerators, have gradually received more attention for accelerating the neural network computations.  ...  (2019) trained a neural network with injection noise to make the model weights less sensitive to variation of noise.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.03230v2">arXiv:2007.03230v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k72nba2bsrhjpfwqgqzd7s6vna">fatcat:k72nba2bsrhjpfwqgqzd7s6vna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200903232643/https://arxiv.org/pdf/2007.03230v1.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0d/4a/0d4afb96310940ee76710009bc37cdc17a9951bb.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.03230v2" 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>

Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation [article]

Chuteng Zhou, Prad Kadambi, Matthew Mattina, Paul N. Whatmough
<span title="2020-01-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we advance the understanding of noisy neural networks.  ...  Our method achieves models with as much as two times greater noise tolerance compared with the previous best attempts, which is a significant step towards making analog hardware practical for deep learning  ...  Section 4 presents a more formal analysis of noisy neural networks. Section 5 gives a distillation methodology for training noisy neural networks, with experimental results.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.04974v1">arXiv:2001.04974v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w36ylu43qbhkxbagjim3ggchue">fatcat:w36ylu43qbhkxbagjim3ggchue</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200825200038/https://arxiv.org/pdf/2001.04974v1.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/66/88/6688a09e910610b2a4dcef116c327e5e1529aaaa.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.04974v1" 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>

Bootstrapping Deep Neural Networks from Approximate Image Processing Pipelines [article]

Kilho Son and Jesse Hostetler and Sek Chai
<span title="2019-02-15">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We intend to replace parts or all of a target pipeline with deep neural networks to achieve benefits such as increased accuracy or reduced computational requirement.  ...  To acquire a large amount of labeled data necessary to train the deep neural network, we propose a workflow that leverages the target pipeline to create a significantly larger labeled training set automatically  ...  Thanks to the robustness in the deep neural networks, the deep neural networks trained with noisy labels outperform the target pipeline.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12108v2">arXiv:1811.12108v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hbxww2u2szc7xeipfyzrv5zp3y">fatcat:hbxww2u2szc7xeipfyzrv5zp3y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200908120058/https://arxiv.org/ftp/arxiv/papers/1811/1811.12108.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/57/1d/571d026898d1b87874c6b345fb3080a0e98d7310.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.12108v2" 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>

Enabling Training of Neural Networks on Noisy Hardware

Tayfun Gokmen
<span title="2021-09-09">2021</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/jfxjod42szdexo7gatfnybn2ca" style="color: black;">Frontiers in Artificial Intelligence</a> </i> &nbsp;
Empirical simulation results show that TTv2 can train various neural networks close to their ideal accuracy even at extremely noisy hardware settings.  ...  In short, we describe an end-to-end training and model extraction technique for extremely noisy crossbar-based analog hardware that can be used to accelerate DNN training workloads and match the performance  ...  Like Model-I, these models are also trained on noisy analog hardware but with slightly relaxed array assumptions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/frai.2021.699148">doi:10.3389/frai.2021.699148</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34568813">pmid:34568813</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8458875/">pmcid:PMC8458875</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rxztadeqcva4hirigysscg7t24">fatcat:rxztadeqcva4hirigysscg7t24</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210914142647/https://fjfsdata01prod.blob.core.windows.net/articles/files/699148/pubmed-zip/.versions/1/.package-entries/frai-04-699148/frai-04-699148.pdf?sv=2018-03-28&amp;sr=b&amp;sig=p%2B5%2BHeFbAeHLfQqnYyg%2FLkQj0wN6REruam%2BL8MxgP5c%3D&amp;se=2021-09-14T14%3A27%3A16Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27frai-04-699148.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/ce/36/ce3614d25cb204cdbe9249d52a26a5d93dc5f9df.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/frai.2021.699148"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8458875" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

A novel algorithm for frequency extraction of ABS signals by using DTDNNs

Mohammad Ali SHAFIEIAN, Hamed BANIZAMAN, Shahrzad SEDAGHAT
<span title="2019-05-15">2019</span> <i title="The Scientific and Technological Research Council of Turkey"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ewkcv4t6w5f2pc7j2w426gox7a" style="color: black;">Turkish Journal of Electrical Engineering and Computer Sciences</a> </i> &nbsp;
In this paper, a novel method for frequency extraction is introduced in which one type of neural network, the distributed time-delay neural network (DTDNN), is used.  ...  Simulation results show that the output of the neural network can acceptably follow frequency variations of ABS signals after convergence.  ...  ABS signal processing with neural network There are various approaches to extracting the fundamental component of frequency from a noisy ABS signal [6, 10, 11, 14, 15] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3906/elk-1712-397">doi:10.3906/elk-1712-397</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ry23woj2w5hczctughcjpsv46q">fatcat:ry23woj2w5hczctughcjpsv46q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200209183849/http://journals.tubitak.gov.tr/elektrik/issues/elk-19-27-3/elk-27-3-14-1712-397.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/06/0d/060d9d82e5344e966eba4f4d4e0b3251043c865c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3906/elk-1712-397"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Fringe Pattern Denoising using U-Net based neural network

J. M. Crespo, V. Moreno, Juan Ramón Rabuñal, Alejandro Pazos, Monica Canabal Carbia, H. Michinel, M.F. Costa, O. Frazao
<span title="">2020</span> <i title="EDP Sciences"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/oduy4e4fvfhovftixyndrlkomi" style="color: black;">EPJ Web of Conferences</a> </i> &nbsp;
We test the use U-Net deep convolutional network applied to the obtained interference images, trained with an ad-hoc generated image dataset with complex fringe patterns, computed using high order Zernike  ...  Acknowledgments Data Availability A test dataset, script and the model definition to check the results with a sample subset have been deposited in the GitHub repository: https://github.com/jmcrespoc/  ...  This set was the ground true for the inputs and for the noisy images in the training dataset, we included an additive and random noise component based on a normal distribution to align the noisy images  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1051/epjconf/202023806009">doi:10.1051/epjconf/202023806009</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/om3dukkbx5a3blbncmuhwmbnqe">fatcat:om3dukkbx5a3blbncmuhwmbnqe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200821163015/https://www.epj-conferences.org/articles/epjconf/pdf/2020/14/epjconf_eosam2020_06009.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/ae/1e/ae1eeb2fa34e2a080bd35da807ad7750499a6a7a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1051/epjconf/202023806009"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Quantum error reduction with deep neural network applied at the post-processing stage [article]

A. A. Zhukov, W. V. Pogosov
<span title="2021-11-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The network is trained to transform data obtained from quantum hardware with artificially increased Trotter steps number towards the data obtained without such an increase.  ...  Deep neural networks (DNN) can be applied at the post-processing stage for the improvement of the results of quantum computations on noisy intermediate-scale quantum (NISQ) processors.  ...  Similar data but affected by hardware imperfections can be obtained as outcomes from a noisy quantum computer. Next, the neural network can be trained to transform noisy data towards ideal results.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.07793v3">arXiv:2105.07793v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tpzk7miwhvdcddp4q2dou7ctr4">fatcat:tpzk7miwhvdcddp4q2dou7ctr4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210520081104/https://arxiv.org/pdf/2105.07793v1.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3c/bc/3cbcc5f030b8088dbb6b57c488a11deb947b0b51.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.07793v3" 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 artificial neural network as a software sensor for optimal control of a wastewater treatment process

Dong-Jin Choi, Heekyung Park
<span title="">2001</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ge6v5555gze5zbpoiatmjdlhli" style="color: black;">Water Research</a> </i> &nbsp;
Multivariate regression, artificial neural networks (ANN), and a hybrid technique that combines principal component analysis as a preprocessing stage are applied to data from industrial wastewater processes  ...  Many parameters cannot be measured directly with on-line sensors.  ...  Fig. 4 . 4 Hybrid neural network combined with principal component analysis: (a) model structure; (b) the result of hybrid neural network modeling (RMSE=13.82).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0043-1354(01)00134-8">doi:10.1016/s0043-1354(01)00134-8</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/12230179">pmid:12230179</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lhkpxnzymffujbloz7r2eyfsaa">fatcat:lhkpxnzymffujbloz7r2eyfsaa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808160535/http://koasas.kaist.ac.kr/bitstream/10203/14425/1/A%20Hybrid%20Artificial%20Neural%20Network%20as%20a%20Software%20Sensor%20in%20a%20Wastewater%20Treatment%20Process.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/e2/35/e2350d619cc8ca2b07c923bd9fba7a01e6622492.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s0043-1354(01)00134-8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Eigennoise Speech Recovery in Adverse Environments with Joint Compensation of Additive and Convolutive Noise

Trung-Nghia Phung, Huy-Khoi Do, Van-Tao Nguyen, Quang-Vinh Thai
<span title="">2015</span> <i title="Hindawi Limited"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q3mxefpbk5efhma3hzwc6vmjx4" style="color: black;">Advances in Acoustics and Vibration</a> </i> &nbsp;
, especially in adverse environments with joint compensation of additive and convolutive noises.  ...  We also proposed a noise adaptation for speech recovery with the eigennoise similar to the eigenvoice in voice conversion.  ...  Recent advances in computer hardware researches and applications reduce the difficulty of training with gigantic corpus.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2015/170183">doi:10.1155/2015/170183</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6lbbp2bn7rh53du5bqdsmvoucq">fatcat:6lbbp2bn7rh53du5bqdsmvoucq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200208165239/http://downloads.hindawi.com/archive/2015/170183.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/5d/69/5d694e0175f905b89e521edd2e24fdcf7179922d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1155/2015/170183"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> hindawi.com </button> </a>

Harnessing Optoelectronic Noises in a Photonic Generative Adversarial Network (GAN) [article]

Changming Wu, Xiaoxuan Yang, Heshan Yu, Ruoming Peng, Ichiro Takeuchi, Yiran Chen, Mo Li
<span title="2021-09-17">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
noise to the network, and implementing the trained network with resilience to hardware non-idealities.  ...  Surprisingly, the photonic GAN with hardware noises and inaccuracies can generate images of even higher quality than the noiseless software baseline.  ...  In contrast, a discriminative network's inference accuracy always decreases with more noisy hardware 37,38 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.08622v1">arXiv:2109.08622v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uicgbztthfffneouyqmmw3bo6q">fatcat:uicgbztthfffneouyqmmw3bo6q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210921031708/https://arxiv.org/ftp/arxiv/papers/2109/2109.08622.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/16/52/1652456e3e071c9d95a4e8ba5aba44c5ff08428e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.08622v1" 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>

Memory efficient on-line streaming for multichannel spike train analysis

Bo Yu, T. Mak, L. Smith, Yihe Sun, A. Yakovlev, Chi-Sang Poon
<span title="">2011</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/i3wdcpisqrhohjypmlikfya2la" style="color: black;">2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society</a> </i> &nbsp;
In this paper, we present a streaming method for implementing real-time memory efficient neural signal processing hardware.  ...  BMI) system in terms of power dissipation and hardware area.  ...  Using generated spike firing times, the spike train synthesis tool generates noisy spike train through specifying the number of neurons, neuronal spike shapes and signal to noise ratio of spike train.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iembs.2011.6090648">doi:10.1109/iembs.2011.6090648</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/22254804">pmid:22254804</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/embc/YuMSSYP11.html">dblp:conf/embc/YuMSSYP11</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mlcawcc2ifeb3adfsx7tbyplie">fatcat:mlcawcc2ifeb3adfsx7tbyplie</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20120130213500/http://www.cs.stir.ac.uk/~lss/recentpapers/Memory%20Efficient%20On-Line%20Streaming%20for%20Multichannel%20Spike%20Train%20Analysis.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/2b/1d/2b1d2062bcf2063cbb9cad22d218c9193e2a4c6f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iembs.2011.6090648"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Nanophotonic Reservoir Computing for Noisy Time Series Classification

M. R. Salehi, E. Abiri, L. Dehyadegari
<span title="">2014</span> <i title="IACSIT Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7wdo44rafbg5rfskrbd6snu7yy" style="color: black;">International Journal of Computer and Electrical Engineering</a> </i> &nbsp;
Reservoir computing is known as a recent training concept in machine learning. This method is particularly useful in solving a broad category of categorization and recognition problems.  ...  The aim of this paper is using photonic reservoir computing for noisy time series classification. A complex network of photonic crystal cavities is used for modeling photonic reservoir computing.  ...  Since the training of weights is limited to the readout function, it is much simpler than that of other neural networks to have a hardware implementation of this structure.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7763/ijcee.2014.v6.830">doi:10.7763/ijcee.2014.v6.830</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wf62pnxj35hthoniy5iakwwn7i">fatcat:wf62pnxj35hthoniy5iakwwn7i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170812082305/http://ijcee.org/papers/830-G0005.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/99/9d9983366a1754cb1e381d5ade3a108665b0f470.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.7763/ijcee.2014.v6.830"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Conditional Born machine for Monte Carlo events generation [article]

Oriel Kiss, Michele Grossi, Enrique Kajomovitz, Sofia Vallecorsa
<span title="2022-05-16">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Models are run on (noisy) simulators and IBM Quantum superconducting quantum hardware.  ...  Empirical evidences suggest that Born machines can reproduce the underlying distribution of datasets coming from Monte Carlo simulations, and are competitive with classical machine learning-based generative  ...  Nevertheless, difficulties are observed during the training on hardware and noisy simulators, which could be an effect of noise-induced BP [52] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.07674v1">arXiv:2205.07674v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5jz7nt2qmjestmpzaz2ynb3xxi">fatcat:5jz7nt2qmjestmpzaz2ynb3xxi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220518125651/https://arxiv.org/pdf/2205.07674v1.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/1d/cc/1dcc7e2f346221e849a64a1b45158b18cda0f122.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.07674v1" 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>

CMOS Circuit Implementation of Spiking Neural Network for Pattern Recognition Using On-chip Unsupervised STDP Learning [article]

Sahibia Kaur Vohra, Sherin A Thomas, Mahendra Sakare, Devarshi Mrinal Das
<span title="2022-04-09">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
It does not involve the use of FPGAs, CPUs or GPUs for training the neural network.  ...  Spiking neural network (SNN) with bio-inspired spike-timing-dependent plasticity learning (STDP) is a promising solution for energy-efficient neuromorphic systems than conventional artificial neural network  ...  The more efficient way is to do both training and inference in SNN hardware.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.04430v1">arXiv:2204.04430v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xfrssaacn5celfovendwepp4ni">fatcat:xfrssaacn5celfovendwepp4ni</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220520074100/https://arxiv.org/pdf/2204.04430v1.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/9a/4a/9a4a7635c57e7e0adde7495bfeb0dbdbf32718ad.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.04430v1" 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>

Optimizing Memory Placement using Evolutionary Graph Reinforcement Learning [article]

Shauharda Khadka, Estelle Aflalo, Mattias Marder, Avrech Ben-David, Santiago Miret, Shie Mannor, Tamir Hazan, Hanlin Tang, Somdeb Majumdar
<span title="2020-10-15">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We train and validate our approach directly on the Intel NNP-I chip for inference.  ...  The growing complexity of neural networks calls for automated memory mapping instead of manual heuristic approaches; yet the search space of neural network computational graphs have previously been prohibitively  ...  EGRL, a scalable population-based algorithm that can effectively train on sparse and noisy feedback from the host hardware in large search spaces. 3.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.07298v2">arXiv:2007.07298v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bmeoaubufjd6hccqh6edcnnfyu">fatcat:bmeoaubufjd6hccqh6edcnnfyu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201023120350/https://arxiv.org/pdf/2007.07298v2.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/c6/47/c647bdb07d9efd8cd2e45dfffd57c08c975f63e9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2007.07298v2" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 16,338 results