Filters








29,000 Hits in 7.0 sec

Learning Factored Representations in a Deep Mixture of Experts [article]

David Eigen, Marc'Aurelio Ranzato, Ilya Sutskever
<span title="2014-03-09">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this this work, we extend the Mixture of Experts to a stacked model, the Deep Mixture of Experts, with multiple sets of gating and experts.  ...  On a randomly translated version of the MNIST dataset, we find that the Deep Mixture of Experts automatically learns to develop location-dependent ("where") experts at the first layer, and class-specific  ...  Mixture of Experts [9] , which learns a hierarchy of gating networks in a tree structure.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1312.4314v3">arXiv:1312.4314v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/r34deido25h77kbsdpucgb6m5e">fatcat:r34deido25h77kbsdpucgb6m5e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200916125726/https://arxiv.org/pdf/1312.4314v3.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/44/dd/44ddac48353ead135eef4096859956eaa31be2a5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1312.4314v3" 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>

Modularity Matters: Learning Invariant Relational Reasoning Tasks [article]

Jason Jo, Vikas Verma, Yoshua Bengio
<span title="2018-06-18">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
To this end, we consider a modularized variant of the ResNet model, referred to as a Residual Mixture Network (ResMixNet) which employs a mixture-of-experts architecture to interleave distributed representations  ...  The CNN we tested all learn hierarchies of fully distributed features and thus encode the distributed representation prior.  ...  Best viewed in color. (a) M (E, D): A mixture of E experts, where each expert is a D stack of residual modules and a gater network G which weights all the experts and forms an additive mixture.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.06765v1">arXiv:1806.06765v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5fyzwnpppbbslgjcnh4vuqyflq">fatcat:5fyzwnpppbbslgjcnh4vuqyflq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200908221438/https://arxiv.org/pdf/1806.06765v1.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/dc/49/dc49a99fe20a8a401f694c0d0473a1fb1003a310.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1806.06765v1" 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>

Deep Mixture of Diverse Experts for Large-Scale Visual Recognition

Tianyi Zhao, Qiuyu Chen, Zhenzhong Kuang, Jun Yu, Wei Zhang, Ming He, Jianping Fan
<span title="">2018</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3px634ph3vhrtmtuip6xznraqi" style="color: black;">IEEE Transactions on Pattern Analysis and Machine Intelligence</a> </i> &nbsp;
In this paper, a deep mixture of diverse experts algorithm is developed for seamlessly combining a set of base deep CNNs (convolutional neural networks) with diverse outputs (task spaces), e.g., such base  ...  Index Terms-Deep mixture of diverse experts, base deep CNNs, deep multi-task learning, multi-task softmax, large-scale visual recognition.  ...  DEEP MIXTURE OF DIVERSE EXPERTS In this paper, a deep mixture of diverse experts algorithm is developed to recognize tens of thousands of atomic object classes by seamlessly combining a set of base deep  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2018.2828821">doi:10.1109/tpami.2018.2828821</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29993909">pmid:29993909</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/daurhaanhze47b5ss43eh5ndwm">fatcat:daurhaanhze47b5ss43eh5ndwm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190223194854/http://pdfs.semanticscholar.org/4a75/d59c9c57da420441190071ba545eb4a75e1e.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/4a/75/4a75d59c9c57da420441190071ba545eb4a75e1e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/tpami.2018.2828821"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

The Representational Capacity of Action-Value Networks for Multi-Agent Reinforcement Learning [article]

Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson
<span title="2019-04-10">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we empirically investigate the representational power of various network architectures on a series of one-shot games.  ...  Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success.  ...  Figure 4 : 4 Reconstructed Q(a) for the Climb Game (a) factored Q function learning approach, and (b) the mixture of experts learning approach.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.07497v3">arXiv:1902.07497v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5njf7zaocrgwzby2b6odokfmiy">fatcat:5njf7zaocrgwzby2b6odokfmiy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200829173953/https://arxiv.org/pdf/1902.07497v3.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/26/1d262db06960d4513f640d181634c6d131389f05.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1902.07497v3" 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>

Learning Deep Representation Without Parameter Inference for Nonlinear Dimensionality Reduction [article]

Xiao-Lei Zhang
<span title="2014-01-02">2014</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Unsupervised deep learning is one of the most powerful representation learning techniques.  ...  Experimental results show that the proposed deep model can learn better representations than deep belief networks and meanwhile can train a much larger network with much less time than deep belief networks  ...  Introduction Deep learning [1, 2] is one of the most powerful representation learning techniques.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1308.4922v2">arXiv:1308.4922v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3j3yiq6lwfbbtlixqc52kkml64">fatcat:3j3yiq6lwfbbtlixqc52kkml64</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200905143513/https://arxiv.org/pdf/1308.4922v1.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/f6/85/f68508d26a3baf5c13c2625c843c04d2d1327589.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1308.4922v2" 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>

Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning

Jacopo Castellini, Frans A. Oliehoek, Rahul Savani, Shimon Whiteson
<span title="2021-06-07">2021</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/7rdrzlhoxjb5ho2u76erh6zpni" style="color: black;">Autonomous Agents and Multi-Agent Systems</a> </i> &nbsp;
In this work, we empirically investigate the learning power of various network architectures on a series of one-shot games.  ...  AbstractRecent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success.  ...  To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10458-021-09506-w">doi:10.1007/s10458-021-09506-w</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34720685">pmid:34720685</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8550438/">pmcid:PMC8550438</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w6orhpwv3jh4vojzcshv2qklwq">fatcat:w6orhpwv3jh4vojzcshv2qklwq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210715152519/https://repository.tudelft.nl/islandora/object/uuid%3A49288083-b5f9-431f-8371-47dc4b789134/datastream/OBJ/download" 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/2a/7d/2a7d883d0b0b6e6a29376fffab8979da77064441.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s10458-021-09506-w"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8550438" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Tree-gated Deep Mixture-of-Experts For Pose-robust Face Alignment [article]

Estephe Arnaud, Arnaud Dapogny, Kevin Bailly
<span title="2019-10-21">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In order to increase robustness to an ensemble of factors of variations (e.g. head pose or occlusions), a given layer (e.g. a regressor or an upstream CNN layer) can be replaced by a Mixture of Experts  ...  The weights of this mixture can be learned as gating functions to jointly learn the experts and the corresponding weights.  ...  Acknowledgment This work has been supported by the French National Agency (ANR) in the frame of its Technological Research JCJC program (FacIL, project ANR-17-CE33-0002).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.09450v1">arXiv:1910.09450v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/waxrxzo72zb7dd7pnoxi5oyb4i">fatcat:waxrxzo72zb7dd7pnoxi5oyb4i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902021056/https://arxiv.org/pdf/1910.09450v1.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/3a/0f/3a0ffdc12b5d3d5f90b321cf3b0785ada0570a36.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.09450v1" 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>

Opponent Modeling in Deep Reinforcement Learning [article]

He He, Jordan Boyd-Graber, Kevin Kwok, Hal Daumé III
<span title="2016-09-18">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
By using a Mixture-of-Experts architecture, our model automatically discovers different strategy patterns of opponents without extra supervision.  ...  Inspired by the recent success of deep reinforcement learning, we present neural-based models that jointly learn a policy and the behavior of opponents.  ...  Southey, Finnegan, Bowling, Michael, Larson, Bryce, Pic- Learning factored representations in a deep mixture of cione, Carmelo, Burch, Neil, Billings, Darse, and Rayner, experts.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1609.05559v1">arXiv:1609.05559v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bd6p7tzhk5cuhpl4nwtjfwemdi">fatcat:bd6p7tzhk5cuhpl4nwtjfwemdi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200914210944/https://arxiv.org/pdf/1609.05559v1.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/d9/3f/d93fb5ceab0ab717a290f7b556ef595df1ef1634.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1609.05559v1" 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>

Gated Ensemble of Spatio-temporal Mixture of Experts for Multi-task Learning in Ride-hailing System [article]

M. H. Rahman, S. M. Rifaat, S. N. Sadeek, M. Abrar, D. Wang
<span title="2021-01-05">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Therefore, a multi-task learning architecture is proposed in this study by developing gated ensemble of spatio-temporal mixture of experts network (GESME-Net) with convolutional recurrent neural network  ...  Furthermore, an input agnostic feature weighting layer is integrated with the architecture for learning joint representation in multi-task learning and revealing the contribution of the input features  ...  Mixture of Experts Mixture of experts were initially developed as an ensemble method (Jacobs, Jordan, Nowlan, & Hinton, 1991) and later utilized as stacked layers in deep learning models (Eigen, Ranzato  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.15408v2">arXiv:2012.15408v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kzrvaxlbrzdg7bdcmzghk4grgu">fatcat:kzrvaxlbrzdg7bdcmzghk4grgu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210112093605/https://arxiv.org/ftp/arxiv/papers/2012/2012.15408.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/02/10/0210acef93ce969040c71dbc7c36ad68c0e22067.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.15408v2" 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>

Stochastic-Expert Variational Autoencoder for Collaborative Filtering

Yoon-Sik Cho, Min-hwan Oh
<span title="2022-04-25">2022</span> <i title="ACM"> Proceedings of the ACM Web Conference 2022 </i> &nbsp;
selection, which allows the model to learn a richer and more complex latent representation of user preferences.  ...  Motivated by the recent successes of deep generative models used for collaborative filtering, we propose a novel framework of VAE for collaborative filtering using multiple experts and stochastic expert  ...  to learn richer and complex latent representation of user preferences.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3485447.3512120">doi:10.1145/3485447.3512120</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/km4bnt35inemfjvrpt2vrougx4">fatcat:km4bnt35inemfjvrpt2vrougx4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220504170053/https://dl.acm.org/doi/pdf/10.1145/3485447.3512120" 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/51/2b/512b0e99d908563b4a91d94ba7c120e4c16e6a97.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3485447.3512120"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

One Model To Learn Them All [article]

Lukasz Kaiser, Aidan N. Gomez, Noam Shazeer, Ashish Vaswani, Niki Parmar, Llion Jones, Jakob Uszkoreit
<span title="2017-06-16">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
But for each problem, getting a deep model to work well involves research into the architecture and a long period of tuning.  ...  Deep learning yields great results across many fields, from speech recognition, image classification, to translation.  ...  Conclusions We demonstrate, for the first time, that a single deep learning model can jointly learn a number of large-scale tasks from multiple domains.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1706.05137v1">arXiv:1706.05137v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dd3xaewfanbcbbuk36silqsfyi">fatcat:dd3xaewfanbcbbuk36silqsfyi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200826203709/https://arxiv.org/pdf/1706.05137v1.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/50/61/5061f591aa8ff224cd20cdcb3b62d156fb187bed.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1706.05137v1" 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>

Exploiting Out-of-Domain Datasets and Visual Representations for Image Sentiment Classification

Alexandros Pournaras, Nikolaos Gkalelis, Damianos Galanopoulos, Vasileios Mezaris
<span title="2021-11-05">2021</span> <i title="Zenodo"> Zenodo </i> &nbsp;
We also evaluate a Mixture of Experts approach, for learning from this combination of representations, and highlight its performance advantages.  ...  The most recent works are based on deep convolutional neural networks, and exploit transfer learning from other image classification tasks.  ...  Mixture of Experts The original formulation of Mixture of Experts (MoE) was introduced in [20] as a learning procedure involving several "expert" networks that implicitly learn different subsets of the  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.5710032">doi:10.5281/zenodo.5710032</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fwbf6t3owbf3hapvix3sshwgea">fatcat:fwbf6t3owbf3hapvix3sshwgea</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220203210528/https://zenodo.org/record/5710033/files/smap2021_preprint.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/04/e5/04e5de0656dda3eb0b9772bbd635e0fb7948fd83.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.5710032"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Anchoring to Exemplars for Training Mixture-of-Expert Cell Embeddings [article]

Siqi Wang, Manyuan Lu, Nikita Moshkov, Juan C. Caicedo, Bryan A. Plummer
<span title="2021-12-06">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose Treatment ExemplArs with Mixture-of-experts (TEAMs), an embedding learning approach that learns a set of experts that are specialized in capturing technical variations in our training set and  ...  Thus, TEAMs can learn powerful embeddings with less technical variation bias by minimizing the noise from every expert.  ...  Our mixtures-of-experts representation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.03208v1">arXiv:2112.03208v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dem557uqwjavboekwtwimk66hi">fatcat:dem557uqwjavboekwtwimk66hi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211208081329/https://arxiv.org/pdf/2112.03208v1.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/74/08/7408d4c6917294c6297ca42de7cce06f8c246eb8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.03208v1" 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>

Phenotypical Ontology Driven Framework for Multi-Task Learning [article]

Mohamed Ghalwash, Zijun Yao, Prithwish Chakraborty, James Codella, Daby Sow
<span title="2020-09-04">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The key contribution of our work is the effective use of knowledge from a predefined well-established medical relationship graph (ontology) to construct a novel deep learning network architecture that  ...  It can effectively leverage knowledge from a well-established medical relationship graph (ontology) by constructing a deep learning network architecture that mirrors this graph.  ...  The model has a shared representation layer, called experts, to learn different mixture of representations.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.02188v1">arXiv:2009.02188v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/f3fd5t5rlbgrlnflwzfzrnmiya">fatcat:f3fd5t5rlbgrlnflwzfzrnmiya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201119013300/https://arxiv.org/ftp/arxiv/papers/2009/2009.02188.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/b0/9b/b09b7b3a26d106014f6585d86b51054afae45bf2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.02188v1" 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>

Latent Variable Algorithms for Multimodal Learning and Sensor Fusion [article]

Lijiang Guo
<span title="2019-04-23">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Multimodal learning has been lacking principled ways of combining information from different modalities and learning a low-dimensional manifold of meaningful representations.  ...  In the second part, we focus on recovering the manifold of latent representation.  ...  Acknowledgement Part of this work is based on Lijiang Guo's PhD qualify exam paper. We would like to thank Dr. Geoffrey Fox, Dr. Minje Kim, Dr. Francesco Nesta, Dr. Michael Ryoo and Dr.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.10450v1">arXiv:1904.10450v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6634ghs74fcd3fz3l4nov4rb3m">fatcat:6634ghs74fcd3fz3l4nov4rb3m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200823142816/https://arxiv.org/pdf/1904.10450v1.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/af/e4/afe43ef0f06299d375a97c0244fdc2c1a20a47dc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1904.10450v1" 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 29,000 results