{"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/adam/papers/242","list_of":"/method/adam","method":"Adam","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":242,"pages_in_order":244,"rows_per_page":100,"rows":[24101,24200],"of":24390,"counts":{"archive_papers_tagged":24390,"with_a_code_link":10944,"where_syntology_ran_a_sample":3424,"not_listed_spam_title":0,"listed":24390,"listed_where_code_ran":3424,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2899,"every_run_a_failure_of_syntologys_instrument":525,"listed_with_a_run_with_no_instrument_failure":2899,"listed_every_run_a_failure_of_syntologys_instrument":525,"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/adam","prev":"/method/adam/papers/241","next":"/method/adam/papers/243","papers":[{"paper":"/paper/hyperadam-a-learnable-task-adaptive-adam-for","slug":"hyperadam-a-learnable-task-adaptive-adam-for","title":"HyperAdam: A Learnable Task-Adaptive Adam for Network Training","date":"2018-11-22","arxiv_id":"1811.08996","n_code_links":2,"syntology":null},{"paper":"/paper/deep-frank-wolfe-for-neural-network","slug":"deep-frank-wolfe-for-neural-network","title":"Deep Frank-Wolfe For Neural Network Optimization","date":"2018-11-19","arxiv_id":"1811.07591","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["oval-group/dfw"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/ivd-net-intervertebral-disc-localization-and","slug":"ivd-net-intervertebral-disc-localization-and","title":"IVD-Net: Intervertebral disc localization and segmentation in MRI with a multi-modal UNet","date":"2018-11-19","arxiv_id":"1811.08305","n_code_links":1,"syntology":null},{"paper":"/paper/gpipe-efficient-training-of-giant-neural","slug":"gpipe-efficient-training-of-giant-neural","title":"GPipe: Efficient Training of Giant Neural Networks using Pipeline Parallelism","date":"2018-11-16","arxiv_id":"1811.06965","n_code_links":13,"syntology":{"ran":20,"of":25,"n_ran_checked":19,"n_instrument":1,"unverified":5,"pointer_only":16,"phrase":"20 ran (of which 0 constructed an object rather than computing a result; 19 with no instrument failure: 0 honoured, 0 violated, 19 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":null,"slug":"modelling-the-dynamic-joint-policy-of","title":"Modelling the Dynamic Joint Policy of Teammates with Attention Multi-agent DDPG","date":"2018-11-13","arxiv_id":"1811.07029","n_code_links":0,"syntology":null},{"paper":null,"slug":"identification-of-internal-faults-in-indirect","title":"Identification of Internal Faults in Indirect Symmetrical Phase Shift Transformers Using Ensemble Learning","date":"2018-11-12","arxiv_id":"1811.04537","n_code_links":0,"syntology":null},{"paper":null,"slug":"input-combination-strategies-for-multi-source-1","title":"Input Combination Strategies for Multi-Source Transformer Decoder","date":"2018-11-12","arxiv_id":"1811.04716","n_code_links":0,"syntology":null},{"paper":"/paper/practical-bayesian-learning-of-neural","slug":"practical-bayesian-learning-of-neural","title":"Practical Bayesian Learning of Neural Networks via Adaptive Optimisation Methods","date":"2018-11-08","arxiv_id":"1811.03679","n_code_links":1,"syntology":null},{"paper":"/paper/ace-an-actor-ensemble-algorithm-for","slug":"ace-an-actor-ensemble-algorithm-for","title":"ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search","date":"2018-11-06","arxiv_id":"1811.02696","n_code_links":1,"syntology":null},{"paper":"/paper/molecular-transformer-for-chemical-reaction","slug":"molecular-transformer-for-chemical-reaction","title":"Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction","date":"2018-11-06","arxiv_id":"1811.02633","n_code_links":1,"syntology":null},{"paper":"/paper/mesh-tensorflow-deep-learning-for","slug":"mesh-tensorflow-deep-learning-for","title":"Mesh-TensorFlow: Deep Learning for Supercomputers","date":"2018-11-05","arxiv_id":"1811.02084","n_code_links":1,"syntology":null},{"paper":"/paper/simple-distributed-and-accelerated","slug":"simple-distributed-and-accelerated","title":"Simple, Distributed, and Accelerated Probabilistic Programming","date":"2018-11-05","arxiv_id":"1811.02091","n_code_links":1,"syntology":null},{"paper":"/paper/sentence-encoders-on-stilts-supplementary","slug":"sentence-encoders-on-stilts-supplementary","title":"Sentence Encoders on STILTs: Supplementary Training on Intermediate Labeled-data Tasks","date":"2018-11-02","arxiv_id":"1811.01088","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-analysis-of-encoder-representations-in","title":"An Analysis of Encoder Representations in Transformer-Based Machine Translation","date":"2018-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"extracting-syntactic-trees-from-transformer","title":"Extracting Syntactic Trees from Transformer Encoder Self-Attentions","date":"2018-11-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"hybrid-self-attention-network-for-machine","title":"Hybrid Self-Attention Network for Machine Translation","date":"2018-11-01","arxiv_id":"1811.00253","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-stochastic-training-for-over","slug":"accelerating-stochastic-training-for-over","title":"Accelerating SGD with momentum for over-parameterized learning","date":"2018-10-31","arxiv_id":"1810.13395","n_code_links":1,"syntology":null},{"paper":null,"slug":"convolutional-self-attention-network","title":"Convolutional Self-Attention Network","date":"2018-10-31","arxiv_id":"1810.13320","n_code_links":0,"syntology":null},{"paper":"/paper/waveglow-a-flow-based-generative-network-for","slug":"waveglow-a-flow-based-generative-network-for","title":"WaveGlow: A Flow-based Generative Network for Speech Synthesis","date":"2018-10-31","arxiv_id":"1811.00002","n_code_links":2,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"weakly-supervised-grammatical-error","title":"Weakly Supervised Grammatical Error Correction using Iterative Decoding","date":"2018-10-31","arxiv_id":"1811.01710","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-attention-mechanisms-in-neural","title":"Parallel Attention Mechanisms in Neural Machine Translation","date":"2018-10-29","arxiv_id":"1810.12427","n_code_links":0,"syntology":null},{"paper":"/paper/recurrent-transformer-networks-for-semantic","slug":"recurrent-transformer-networks-for-semantic","title":"Recurrent Transformer Networks for Semantic Correspondence","date":"2018-10-29","arxiv_id":"1810.12155","n_code_links":1,"syntology":null},{"paper":null,"slug":"three-mechanisms-of-weight-decay","title":"Three Mechanisms of Weight Decay Regularization","date":"2018-10-29","arxiv_id":"1810.12281","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-target-level-sentiment","slug":"semi-supervised-target-level-sentiment","title":"Variational Semi-supervised Aspect-term Sentiment Analysis via Transformer","date":"2018-10-24","arxiv_id":"1810.10437","n_code_links":0,"syntology":null},{"paper":null,"slug":"finding-mixed-nash-equilibria-of-generative","title":"Finding Mixed Nash Equilibria of Generative Adversarial Networks","date":"2018-10-23","arxiv_id":"1811.02002","n_code_links":0,"syntology":null},{"paper":null,"slug":"hierarchical-approaches-for-reinforcement","title":"Hierarchical Approaches for Reinforcement Learning in Parameterized Action Space","date":"2018-10-23","arxiv_id":"1810.09656","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-analysis-of-attention-mechanisms-the-case","title":"An Analysis of Attention Mechanisms: The Case of Word Sense Disambiguation in Neural Machine Translation","date":"2018-10-17","arxiv_id":"1810.07595","n_code_links":0,"syntology":null},{"paper":null,"slug":"dense-multi-path-u-net-for-ischemic-stroke","title":"Dense Multi-path U-Net for Ischemic Stroke Lesion Segmentation in Multiple Image Modalities","date":"2018-10-16","arxiv_id":"1810.07003","n_code_links":0,"syntology":null},{"paper":"/paper/discriminator-rejection-sampling","slug":"discriminator-rejection-sampling","title":"Discriminator Rejection Sampling","date":"2018-10-16","arxiv_id":"1810.06758","n_code_links":1,"syntology":null},{"paper":null,"slug":"metropolis-hastings-view-on-variational","title":"Metropolis-Hastings view on variational inference and adversarial training","date":"2018-10-16","arxiv_id":"1810.07151","n_code_links":0,"syntology":null},{"paper":"/paper/bert-pre-training-of-deep-bidirectional","slug":"bert-pre-training-of-deep-bidirectional","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","date":"2018-10-11","arxiv_id":"1810.04805","n_code_links":534,"syntology":{"ran":300,"of":659,"n_ran_checked":235,"n_instrument":65,"unverified":359,"pointer_only":164,"phrase":"300 ran (of which 75 constructed an object rather than computing a result; 235 with no instrument failure: 17 honoured, 4 violated, 214 with no contract checked; 65 where Syntology's instrument failed) · 359 unverified","official":{"repos":["google-research/bert"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"paper":"/paper/signsgd-with-majority-vote-is-communication","slug":"signsgd-with-majority-vote-is-communication","title":"signSGD with Majority Vote is Communication Efficient And Fault Tolerant","date":"2018-10-11","arxiv_id":"1810.05291","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":null}},{"paper":"/paper/parametrized-deep-q-networks-learning","slug":"parametrized-deep-q-networks-learning","title":"Parametrized Deep Q-Networks Learning: Reinforcement Learning with Discrete-Continuous Hybrid Action Space","date":"2018-10-10","arxiv_id":"1810.06394","n_code_links":5,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/improving-the-transformer-translation-model","slug":"improving-the-transformer-translation-model","title":"Improving the Transformer Translation Model with Document-Level Context","date":"2018-10-08","arxiv_id":"1810.03581","n_code_links":3,"syntology":{"ran":1,"of":12,"n_ran_checked":1,"n_instrument":0,"unverified":11,"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) · 11 unverified","official":{"repos":["Glaceon31/Document-Transformer","thumt/THUMT"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":10,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"convergence-of-the-adam-algorithm-from-a","title":"Convergence and Dynamical Behavior of the ADAM Algorithm for Non-Convex Stochastic Optimization","date":"2018-10-04","arxiv_id":"1810.02263","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-transformer-based-multi-source-automatic","title":"A Transformer-Based Multi-Source Automatic Post-Editing System","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"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":"an-empirical-study-of-machine-translation-for","title":"An Empirical Study of Machine Translation for the Shared Task of WMT18","date":"2018-10-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/classification-of-medication-related-tweets","slug":"classification-of-medication-related-tweets","title":"Classification of Medication-Related Tweets Using Stacked Bidirectional LSTMs with Context-Aware Attention","date":"2018-10-01","arxiv_id":null,"n_code_links":1,"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/riemannian-adaptive-optimization-methods","slug":"riemannian-adaptive-optimization-methods","title":"Riemannian Adaptive Optimization Methods","date":"2018-10-01","arxiv_id":"1810.00760","n_code_links":1,"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/adashift-decorrelation-and-convergence-of","slug":"adashift-decorrelation-and-convergence-of","title":"AdaShift: Decorrelation and Convergence of Adaptive Learning Rate Methods","date":"2018-09-29","arxiv_id":"1810.00143","n_code_links":3,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":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":"curriculum-goal-masking-for-continuous-deep","title":"Curriculum goal masking for continuous deep reinforcement learning","date":"2018-09-17","arxiv_id":"1809.06146","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":"analysis-of-the-generalization-error","title":"Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black-Scholes Partial Differential Equations","date":"2018-09-09","arxiv_id":"1809.03062","n_code_links":0,"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/mesonet-a-compact-facial-video-forgery","slug":"mesonet-a-compact-facial-video-forgery","title":"MesoNet: a Compact Facial Video Forgery Detection Network","date":"2018-09-04","arxiv_id":"1809.00888","n_code_links":8,"syntology":{"ran":1,"of":6,"n_ran_checked":1,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["DariusAf/MesoNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"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/generative-adversarial-network-with-spatial","slug":"generative-adversarial-network-with-spatial","title":"Generative Adversarial Network with Spatial Attention for Face Attribute Editing","date":"2018-09-01","arxiv_id":null,"n_code_links":1,"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":"/paper/swapnet-garment-transfer-in-single-view","slug":"swapnet-garment-transfer-in-single-view","title":"SwapNet: Garment Transfer in Single View Images","date":"2018-09-01","arxiv_id":null,"n_code_links":1,"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/adversarial-deep-reinforcement-learning-in","slug":"adversarial-deep-reinforcement-learning-in","title":"Adversarial Deep Reinforcement Learning in Portfolio Management","date":"2018-08-29","arxiv_id":"1808.09940","n_code_links":5,"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/backtracking-gradient-descent-method-for","slug":"backtracking-gradient-descent-method-for","title":"Backtracking gradient descent method for general $C^1$ functions, with applications to Deep Learning","date":"2018-08-15","arxiv_id":"1808.05160","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-convergence-of-weighted-adagrad-with","title":"A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration","date":"2018-08-10","arxiv_id":"1808.03408","n_code_links":0,"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":null,"slug":"on-the-convergence-of-a-class-of-adam-type","title":"On the Convergence of A Class of Adam-Type Algorithms for Non-Convex Optimization","date":"2018-08-08","arxiv_id":"1808.02941","n_code_links":0,"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":"/paper/cornernet-detecting-objects-as-paired","slug":"cornernet-detecting-objects-as-paired","title":"CornerNet: Detecting Objects as Paired Keypoints","date":"2018-08-03","arxiv_id":"1808.01244","n_code_links":5,"syntology":{"ran":3,"of":11,"n_ran_checked":1,"n_instrument":2,"unverified":8,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","official":{"repos":["princeton-vl/CornerNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":8,"ran_from_kinds":["official"]}}},{"paper":"/paper/gold-standard-annotations-for-preposition-and","slug":"gold-standard-annotations-for-preposition-and","title":"Gold Standard Annotations for Preposition and Verb Sense with Semantic Role Labels in Adult-Child Interactions","date":"2018-08-01","arxiv_id":null,"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":"/paper/towards-good-practices-on-building-effective","slug":"towards-good-practices-on-building-effective","title":"Towards Good Practices on Building Effective CNN Baseline Model for Person Re-identification","date":"2018-07-29","arxiv_id":"1807.11042","n_code_links":1,"syntology":null},{"paper":null,"slug":"false-positive-reduction-by-actively-mining","title":"False Positive Reduction by Actively Mining Negative Samples for Pulmonary Nodule Detection in Chest Radiographs","date":"2018-07-26","arxiv_id":"1807.10756","n_code_links":0,"syntology":null},{"paper":"/paper/a-unified-theory-of-adaptive-stochastic","slug":"a-unified-theory-of-adaptive-stochastic","title":"Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods","date":"2018-07-19","arxiv_id":"1807.07540","n_code_links":1,"syntology":null},{"paper":"/paper/clarinet-parallel-wave-generation-in-end-to","slug":"clarinet-parallel-wave-generation-in-end-to","title":"ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech","date":"2018-07-19","arxiv_id":"1807.07281","n_code_links":5,"syntology":{"ran":10,"of":13,"n_ran_checked":10,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"convergence-guarantees-for-rmsprop-and-adam","title":"Convergence guarantees for RMSProp and ADAM in non-convex optimization and an empirical comparison to Nesterov acceleration","date":"2018-07-18","arxiv_id":"1807.06766","n_code_links":0,"syntology":null},{"paper":"/paper/bipedal-walking-robot-using-deep","slug":"bipedal-walking-robot-using-deep","title":"Bipedal Walking Robot using Deep Deterministic Policy Gradient","date":"2018-07-16","arxiv_id":"1807.05924","n_code_links":3,"syntology":null}],"record_sha256":"ad69925fdd30f3fc0001f3cd456c92bd1e9679dcdf81109b936781a4ef1c83b7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}