{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/linear-layer/papers/254","list_of":"/method/linear-layer","method":"Linear Layer","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":254,"pages_in_order":255,"rows_per_page":100,"rows":[25301,25400],"of":25421,"counts":{"archive_papers_tagged":25421,"with_a_code_link":11479,"where_syntology_ran_a_sample":3523,"not_listed_spam_title":0,"listed":25421,"listed_where_code_ran":3523,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2976,"every_run_a_failure_of_syntologys_instrument":547,"listed_with_a_run_with_no_instrument_failure":2976,"listed_every_run_a_failure_of_syntologys_instrument":547,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/linear-layer","prev":"/method/linear-layer/papers/253","next":"/method/linear-layer/papers/255","papers":[{"paper":null,"slug":"alibaba-submission-for-wmt18-quality","title":"Alibaba Submission for WMT18 Quality Estimation Task","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"alibabas-neural-machine-translation-systems","title":"Alibaba's Neural Machine Translation Systems for WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cuni-submissions-in-wmt18","title":"CUNI Submissions in WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cuni-transformer-neural-mt-system-for-wmt18","title":"CUNI Transformer Neural MT System for WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"input-combination-strategies-for-multi-source","title":"Input Combination Strategies for Multi-Source Transformer Decoder","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-encoder-transformer-network-for","title":"Multi-encoder Transformer Network for Automatic Post-Editing","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-source-transformer-with-combined-losses","title":"Multi-source transformer with combined losses for automatic post editing","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-machine-translation-with-the","title":"Neural Machine Translation with the Transformer and Multi-Source Romance Languages for the Biomedical WMT 2018 task","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"ntts-neural-machine-translation-systems-for","title":"NTT's Neural Machine Translation Systems for WMT 2018","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/set-transformer-a-framework-for-attention","slug":"set-transformer-a-framework-for-attention","title":"Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks","date":"2018-10-01","arxiv_id":"1810.00825","n_code_links":9,"syntology":{"ran":8,"of":9,"n_ran_checked":6,"n_instrument":2,"unverified":1,"pointer_only":4,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 3 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["juho-lee/set_transformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"tencentfmrd-neural-machine-translation-for","title":"TencentFmRD Neural Machine Translation for WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-karlsruhe-institute-of-technology-systems","title":"The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2018","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-mllp-upv-german-english-machine","title":"The MLLP-UPV German-English Machine Translation System for WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-niutrans-machine-translation-system-for","title":"The NiuTrans Machine Translation System for WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-rwth-aachen-university-filtering-system","title":"The RWTH Aachen University Filtering System for the WMT 2018 Parallel Corpus Filtering Task","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-rwth-aachen-university-supervised-machine","slug":"the-rwth-aachen-university-supervised-machine","title":"The RWTH Aachen University Supervised Machine Translation Systems for WMT 2018","date":"2018-10-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"the-university-of-helsinki-submissions-to-the","title":"The University of Helsinki submissions to the WMT18 news task","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-university-of-marylands-chinese-english","title":"The University of Maryland's Chinese-English Neural Machine Translation Systems at WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tildes-machine-translation-systems-for-wmt","slug":"tildes-machine-translation-systems-for-wmt","title":"Tilde's Machine Translation Systems for WMT 2018","date":"2018-10-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/large-scale-gan-training-for-high-fidelity","slug":"large-scale-gan-training-for-high-fidelity","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","date":"2018-09-28","arxiv_id":"1809.11096","n_code_links":35,"syntology":{"ran":28,"of":41,"n_ran_checked":20,"n_instrument":8,"unverified":13,"pointer_only":14,"phrase":"28 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 1 honoured, 2 violated, 17 with no contract checked; 8 where Syntology's instrument failed) · 13 unverified","official":null}},{"paper":"/paper/fast-and-simple-mixture-of-softmaxes-with-bpe","slug":"fast-and-simple-mixture-of-softmaxes-with-bpe","title":"Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation","date":"2018-09-25","arxiv_id":"1809.09296","n_code_links":1,"syntology":null},{"paper":"/paper/neural-speech-synthesis-with-transformer","slug":"neural-speech-synthesis-with-transformer","title":"Neural Speech Synthesis with Transformer Network","date":"2018-09-19","arxiv_id":"1809.08895","n_code_links":6,"syntology":null},{"paper":null,"slug":"nicts-neural-and-statistical-machine","title":"NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task","date":"2018-09-19","arxiv_id":"1809.07037","n_code_links":0,"syntology":null},{"paper":null,"slug":"revisit-multinomial-logistic-regression-in","title":"Revisit Multinomial Logistic Regression in Deep Learning: Data Dependent Model Initialization for Image Recognition","date":"2018-09-17","arxiv_id":"1809.06131","n_code_links":0,"syntology":null},{"paper":"/paper/music-transformer","slug":"music-transformer","title":"Music Transformer","date":"2018-09-12","arxiv_id":"1809.04281","n_code_links":12,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"on-the-alignment-problem-in-multi-head","title":"On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation","date":"2018-09-11","arxiv_id":"1809.03985","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-zoom-a-saliency-based-sampling","slug":"learning-to-zoom-a-saliency-based-sampling","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","date":"2018-09-10","arxiv_id":"1809.03355","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-allocentric-intuitive-physics","title":"Neural Allocentric Intuitive Physics Prediction from Real Videos","date":"2018-09-07","arxiv_id":"1809.03330","n_code_links":0,"syntology":null},{"paper":"/paper/towards-automated-customer-support","slug":"towards-automated-customer-support","title":"Towards Automated Customer Support","date":"2018-09-02","arxiv_id":"1809.00303","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-error-propagation-in-neural-machine","title":"Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter","date":"2018-09-01","arxiv_id":"1809.00120","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-sharing-methods-for-multilingual","slug":"parameter-sharing-methods-for-multilingual","title":"Parameter Sharing Methods for Multilingual Self-Attentional Translation Models","date":"2018-09-01","arxiv_id":"1809.00252","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatio-temporal-transformer-network-for-video","title":"Spatio-temporal Transformer Network for Video Restoration","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cognate-aware-morphological-segmentation-for","title":"Cognate-aware morphological segmentation for multilingual neural translation","date":"2018-08-31","arxiv_id":"1808.10791","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-attention-linguistic-acoustic-decoder","title":"Self-Attention Linguistic-Acoustic Decoder","date":"2018-08-31","arxiv_id":"1808.10678","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-memad-submission-to-the-wmt18-multimodal","title":"The MeMAD Submission to the WMT18 Multimodal Translation Task","date":"2018-08-31","arxiv_id":"1808.10802","n_code_links":0,"syntology":null},{"paper":"/paper/semi-autoregressive-neural-machine","slug":"semi-autoregressive-neural-machine","title":"Semi-Autoregressive Neural Machine Translation","date":"2018-08-26","arxiv_id":"1808.08583","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["chqiwang/sa-nmt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/training-deeper-neural-machine-translation","slug":"training-deeper-neural-machine-translation","title":"Training Deeper Neural Machine Translation Models with Transparent Attention","date":"2018-08-22","arxiv_id":"1808.07561","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-exploit-invariances-in-clinical","title":"Learning to Exploit Invariances in Clinical Time-Series Data using Sequence Transformer Networks","date":"2018-08-21","arxiv_id":"1808.06725","n_code_links":0,"syntology":null},{"paper":"/paper/larnn-linear-attention-recurrent-neural","slug":"larnn-linear-attention-recurrent-neural","title":"LARNN: Linear Attention Recurrent Neural Network","date":"2018-08-16","arxiv_id":"1808.05578","n_code_links":1,"syntology":null},{"paper":"/paper/character-level-language-modeling-with-deeper","slug":"character-level-language-modeling-with-deeper","title":"Character-Level Language Modeling with Deeper Self-Attention","date":"2018-08-09","arxiv_id":"1808.04444","n_code_links":1,"syntology":null},{"paper":"/paper/design-challenges-in-named-entity","slug":"design-challenges-in-named-entity","title":"Design Challenges in Named Entity Transliteration","date":"2018-08-07","arxiv_id":"1808.02563","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-machine-translation-with-decoding","title":"Neural Machine Translation with Decoding History Enhanced Attention","date":"2018-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"doubly-attentive-transformer-machine","title":"Doubly Attentive Transformer Machine Translation","date":"2018-07-30","arxiv_id":"1807.11605","n_code_links":0,"syntology":null},{"paper":"/paper/reenactgan-learning-to-reenact-faces-via","slug":"reenactgan-learning-to-reenact-faces-via","title":"ReenactGAN: Learning to Reenact Faces via Boundary Transfer","date":"2018-07-29","arxiv_id":"1807.11079","n_code_links":1,"syntology":null},{"paper":null,"slug":"destnet-densely-fused-spatial-transformer","title":"DeSTNet: Densely Fused Spatial Transformer Networks","date":"2018-07-11","arxiv_id":"1807.04050","n_code_links":0,"syntology":null},{"paper":"/paper/big-little-net-an-efficient-multi-scale","slug":"big-little-net-an-efficient-multi-scale","title":"Big-Little Net: An Efficient Multi-Scale Feature Representation for Visual and Speech Recognition","date":"2018-07-10","arxiv_id":"1807.03848","n_code_links":3,"syntology":null},{"paper":"/paper/representation-learning-with-contrastive","slug":"representation-learning-with-contrastive","title":"Representation Learning with Contrastive Predictive Coding","date":"2018-07-10","arxiv_id":"1807.03748","n_code_links":28,"syntology":{"ran":35,"of":45,"n_ran_checked":30,"n_instrument":5,"unverified":10,"pointer_only":22,"phrase":"35 ran (of which 21 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","official":null}},{"paper":"/paper/universal-transformers","slug":"universal-transformers","title":"Universal Transformers","date":"2018-07-10","arxiv_id":"1807.03819","n_code_links":8,"syntology":{"ran":17,"of":25,"n_ran_checked":17,"n_instrument":0,"unverified":8,"pointer_only":24,"phrase":"17 ran (of which 8 constructed an object rather than computing a result; 17 with no instrument failure: 1 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["tensorflow/tensor2tensor"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"model-based-hand-pose-estimation-for","title":"Model-based Hand Pose Estimation for Generalized Hand Shape with Appearance Normalization","date":"2018-07-02","arxiv_id":"1807.00898","n_code_links":0,"syntology":null},{"paper":"/paper/conceptual-captions-a-cleaned-hypernymed","slug":"conceptual-captions-a-cleaned-hypernymed","title":"Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning","date":"2018-07-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/how-much-attention-do-you-need-a-granular","slug":"how-much-attention-do-you-need-a-granular","title":"How Much Attention Do You Need? A Granular Analysis of Neural Machine Translation Architectures","date":"2018-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/kernelized-synaptic-weight-matrices","slug":"kernelized-synaptic-weight-matrices","title":"Kernelized Synaptic Weight Matrices","date":"2018-07-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"learning-longer-term-dependencies-in-rnns-1","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","date":"2018-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-turn-response-selection-for-chatbots","slug":"multi-turn-response-selection-for-chatbots","title":"Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network","date":"2018-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"nict-self-training-approach-to-neural-machine","title":"NICT Self-Training Approach to Neural Machine Translation at NMT-2018","date":"2018-07-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-annotated-transformer","slug":"the-annotated-transformer","title":"The Annotated Transformer","date":"2018-07-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparison-of-transformer-and-recurrent","title":"A Comparison of Transformer and Recurrent Neural Networks on Multilingual Neural Machine Translation","date":"2018-06-18","arxiv_id":"1806.06957","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-lip-reading-a-comparison-of-models-and","title":"Deep Lip Reading: a comparison of models and an online application","date":"2018-06-15","arxiv_id":"1806.06053","n_code_links":0,"syntology":null},{"paper":"/paper/an-evaluation-of-neural-machine-translation","slug":"an-evaluation-of-neural-machine-translation","title":"An Evaluation of Neural Machine Translation Models on Historical Spelling Normalization","date":"2018-06-13","arxiv_id":"1806.05210","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilingual-end-to-end-speech-recognition","title":"Multilingual End-to-End Speech Recognition with A Single Transformer on Low-Resource Languages","date":"2018-06-12","arxiv_id":"1806.05059","n_code_links":0,"syntology":null},{"paper":"/paper/improving-language-understanding-by","slug":"improving-language-understanding-by","title":"Improving Language Understanding by Generative Pre-Training","date":"2018-06-11","arxiv_id":null,"n_code_links":13,"syntology":null},{"paper":null,"slug":"meta-learner-with-linear-nulling","title":"Meta-Learner with Linear Nulling","date":"2018-06-04","arxiv_id":"1806.01010","n_code_links":0,"syntology":null},{"paper":"/paper/deep-diffeomorphic-transformer-networks","slug":"deep-diffeomorphic-transformer-networks","title":"Deep Diffeomorphic Transformer Networks","date":"2018-06-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/direct-shape-regression-networks-for-end-to","slug":"direct-shape-regression-networks-for-end-to","title":"Direct Shape Regression Networks for End-to-End Face Alignment","date":"2018-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"weakly-supervised-phrase-localization-with","title":"Weakly Supervised Phrase Localization With Multi-Scale Anchored Transformer Network","date":"2018-06-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/theory-and-experiments-on-vector-quantized","slug":"theory-and-experiments-on-vector-quantized","title":"Theory and Experiments on Vector Quantized Autoencoders","date":"2018-05-28","arxiv_id":"1805.11063","n_code_links":2,"syntology":null},{"paper":null,"slug":"a-comparison-of-modeling-units-in-sequence-to","title":"A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese","date":"2018-05-16","arxiv_id":"1805.06239","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-data-driven-residential-transformer","title":"A Data-Driven Residential Transformer Overloading Risk Assessment Method","date":"2018-05-02","arxiv_id":"1805.00630","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-neural-transformer-via-an","slug":"accelerating-neural-transformer-via-an","title":"Accelerating Neural Transformer via an Average Attention Network","date":"2018-05-02","arxiv_id":"1805.00631","n_code_links":1,"syntology":{"ran":7,"of":19,"n_ran_checked":7,"n_instrument":0,"unverified":12,"pointer_only":0,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 12 unverified","official":{"repos":["bzhangXMU/transformer-aan"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":12,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"localization-a-missing-link-in-the-pipeline","title":"Localization: A Missing Link in the Pipeline of Object Matching and Registration","date":"2018-05-01","arxiv_id":"1805.00223","n_code_links":0,"syntology":null},{"paper":null,"slug":"craft-complementary-recommendations-using","title":"CRAFT: Complementary Recommendations Using Adversarial Feature Transformer","date":"2018-04-29","arxiv_id":"1804.10871","n_code_links":0,"syntology":null},{"paper":null,"slug":"cram-clued-recurrent-attention-model","title":"CRAM: Clued Recurrent Attention Model","date":"2018-04-28","arxiv_id":"1804.10844","n_code_links":0,"syntology":null},{"paper":"/paper/syllable-based-sequence-to-sequence-speech","slug":"syllable-based-sequence-to-sequence-speech","title":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese","date":"2018-04-28","arxiv_id":"1804.10752","n_code_links":1,"syntology":null},{"paper":"/paper/the-best-of-both-worlds-combining-recent","slug":"the-best-of-both-worlds-combining-recent","title":"The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation","date":"2018-04-26","arxiv_id":"1804.09849","n_code_links":3,"syntology":null},{"paper":null,"slug":"multi-head-decoder-for-end-to-end-speech","title":"Multi-Head Decoder for End-to-End Speech Recognition","date":"2018-04-22","arxiv_id":"1804.08050","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformation-on-computer-generated-facial","title":"Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector","date":"2018-04-12","arxiv_id":"1804.04418","n_code_links":0,"syntology":null},{"paper":"/paper/adafactor-adaptive-learning-rates-with","slug":"adafactor-adaptive-learning-rates-with","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","date":"2018-04-11","arxiv_id":"1804.04235","n_code_links":5,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"statistical-transformer-networks-learning","title":"Statistical transformer networks: learning shape and appearance models via self supervision","date":"2018-04-07","arxiv_id":"1804.02541","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-dense-video-captioning-with-masked","slug":"end-to-end-dense-video-captioning-with-masked","title":"End-to-End Dense Video Captioning with Masked Transformer","date":"2018-04-03","arxiv_id":"1804.00819","n_code_links":1,"syntology":null},{"paper":"/paper/training-tips-for-the-transformer-model","slug":"training-tips-for-the-transformer-model","title":"Training Tips for the Transformer Model","date":"2018-04-01","arxiv_id":"1804.00247","n_code_links":4,"syntology":null},{"paper":null,"slug":"efficient-and-deep-person-re-identification","title":"Efficient and Deep Person Re-Identification using Multi-Level Similarity","date":"2018-03-30","arxiv_id":"1803.11353","n_code_links":0,"syntology":null},{"paper":"/paper/gaan-gated-attention-networks-for-learning-on","slug":"gaan-gated-attention-networks-for-learning-on","title":"GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs","date":"2018-03-20","arxiv_id":"1803.07294","n_code_links":1,"syntology":null},{"paper":"/paper/tensor2tensor-for-neural-machine-translation","slug":"tensor2tensor-for-neural-machine-translation","title":"Tensor2Tensor for Neural Machine Translation","date":"2018-03-16","arxiv_id":"1803.07416","n_code_links":15,"syntology":{"ran":30,"of":48,"n_ran_checked":29,"n_instrument":1,"unverified":18,"pointer_only":0,"phrase":"30 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 0 honoured, 0 violated, 29 with no contract checked; 1 where Syntology's instrument failed) · 18 unverified","official":{"repos":["tensorflow/tensor2tensor"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"studying-invariances-of-trained-convolutional","title":"Studying Invariances of Trained Convolutional Neural Networks","date":"2018-03-15","arxiv_id":"1803.05963","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-decoding-in-sequence-models-using","title":"Fast Decoding in Sequence Models using Discrete Latent Variables","date":"2018-03-09","arxiv_id":"1803.03382","n_code_links":0,"syntology":null},{"paper":"/paper/self-attention-with-relative-position","slug":"self-attention-with-relative-position","title":"Self-Attention with Relative Position Representations","date":"2018-03-06","arxiv_id":"1803.02155","n_code_links":13,"syntology":{"ran":13,"of":23,"n_ran_checked":8,"n_instrument":5,"unverified":10,"pointer_only":3,"phrase":"13 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified","official":{"repos":["tensorflow/tensor2tensor"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/st-gan-spatial-transformer-generative","slug":"st-gan-spatial-transformer-generative","title":"ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing","date":"2018-03-05","arxiv_id":"1803.01837","n_code_links":2,"syntology":{"ran":11,"of":13,"n_ran_checked":11,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["chenhsuanlin/spatial-transformer-GAN"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"classification-based-grasp-detection-using","title":"Classification based Grasp Detection using Spatial Transformer Network","date":"2018-03-04","arxiv_id":"1803.01356","n_code_links":0,"syntology":null},{"paper":"/paper/learning-longer-term-dependencies-in-rnns","slug":"learning-longer-term-dependencies-in-rnns","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","date":"2018-03-01","arxiv_id":"1803.00144","n_code_links":1,"syntology":null},{"paper":null,"slug":"video-person-re-identification-by-temporal","title":"Video Person Re-identification by Temporal Residual Learning","date":"2018-02-22","arxiv_id":"1802.07918","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-spatial-transformer-network","title":"Hierarchical Spatial Transformer Network","date":"2018-01-29","arxiv_id":"1801.09467","n_code_links":0,"syntology":null},{"paper":null,"slug":"identity-preserving-face-recovery-from","title":"Identity-preserving Face Recovery from Portraits","date":"2018-01-08","arxiv_id":"1801.02279","n_code_links":0,"syntology":null},{"paper":"/paper/natural-tts-synthesis-by-conditioning-wavenet","slug":"natural-tts-synthesis-by-conditioning-wavenet","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","date":"2017-12-16","arxiv_id":"1712.05884","n_code_links":33,"syntology":{"ran":7,"of":7,"n_ran_checked":2,"n_instrument":5,"unverified":0,"pointer_only":2,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/sockeye-a-toolkit-for-neural-machine","slug":"sockeye-a-toolkit-for-neural-machine","title":"Sockeye: A Toolkit for Neural Machine Translation","date":"2017-12-15","arxiv_id":"1712.05690","n_code_links":16,"syntology":null},{"paper":"/paper/see-towards-semi-supervised-end-to-end-scene","slug":"see-towards-semi-supervised-end-to-end-scene","title":"SEE: Towards Semi-Supervised End-to-End Scene Text Recognition","date":"2017-12-14","arxiv_id":"1712.05404","n_code_links":2,"syntology":null},{"paper":"/paper/see-towards-semi-supervisedend-to-end-scene","slug":"see-towards-semi-supervisedend-to-end-scene","title":"SEE: Towards Semi-SupervisedEnd-to-End Scene Text Recognition","date":"2017-12-14","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"controllable-top-down-feature-transformer","title":"Controllable Top-down Feature Transformer","date":"2017-12-06","arxiv_id":"1712.02400","n_code_links":0,"syntology":null},{"paper":"/paper/distance-based-self-attention-network-for","slug":"distance-based-self-attention-network-for","title":"Distance-based Self-Attention Network for Natural Language Inference","date":"2017-12-06","arxiv_id":"1712.02047","n_code_links":0,"syntology":null},{"paper":"/paper/state-of-the-art-speech-recognition-with","slug":"state-of-the-art-speech-recognition-with","title":"State-of-the-art Speech Recognition With Sequence-to-Sequence Models","date":"2017-12-05","arxiv_id":"1712.01769","n_code_links":4,"syntology":null},{"paper":null,"slug":"data-fusion-and-machine-learning-integration","title":"Data Fusion and Machine Learning Integration for Transformer Loss of Life Estimation","date":"2017-11-08","arxiv_id":"1711.03398","n_code_links":0,"syntology":null}],"record_sha256":"1cdb1586642db07d2cd58fc1b46643feb38abf63e0860304b228e59529644715","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}