{"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/softmax/papers/364","list_of":"/method/softmax","method":"Softmax","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":364,"pages_in_order":375,"rows_per_page":100,"rows":[36301,36400],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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/softmax","prev":"/method/softmax/papers/363","next":"/method/softmax/papers/365","papers":[{"paper":null,"slug":"nrityantar-pose-oblivious-indian-classical","title":"Nrityantar: Pose oblivious Indian classical dance sequence classification system","date":"2018-12-13","arxiv_id":"1812.05231","n_code_links":0,"syntology":null},{"paper":"/paper/the-pros-and-cons-rank-aware-temporal","slug":"the-pros-and-cons-rank-aware-temporal","title":"The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videos","date":"2018-12-13","arxiv_id":"1812.05538","n_code_links":1,"syntology":null},{"paper":"/paper/cfun-combining-faster-r-cnn-and-u-net-network","slug":"cfun-combining-faster-r-cnn-and-u-net-network","title":"CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation","date":"2018-12-12","arxiv_id":"1812.04914","n_code_links":1,"syntology":null},{"paper":null,"slug":"hyperbolic-deep-learning-for-chinese-natural","title":"Hyperbolic Deep Learning for Chinese Natural Language Understanding","date":"2018-12-11","arxiv_id":"1812.10408","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-discriminative-motion-features","title":"Learning Discriminative Motion Features Through Detection","date":"2018-12-11","arxiv_id":"1812.04172","n_code_links":0,"syntology":null},{"paper":null,"slug":"accelerating-convolutional-neural-networks","title":"Accelerating Convolutional Neural Networks via Activation Map Compression","date":"2018-12-10","arxiv_id":"1812.04056","n_code_links":0,"syntology":null},{"paper":"/paper/learning-embedding-adaptation-for-few-shot","slug":"learning-embedding-adaptation-for-few-shot","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","date":"2018-12-10","arxiv_id":"1812.03664","n_code_links":6,"syntology":null},{"paper":"/paper/planercnn-3d-plane-detection-and","slug":"planercnn-3d-plane-detection-and","title":"PlaneRCNN: 3D Plane Detection and Reconstruction from a Single Image","date":"2018-12-10","arxiv_id":"1812.04072","n_code_links":2,"syntology":null},{"paper":"/paper/sdnet-contextualized-attention-based-deep","slug":"sdnet-contextualized-attention-based-deep","title":"SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering","date":"2018-12-10","arxiv_id":"1812.03593","n_code_links":6,"syntology":null},{"paper":"/paper/von-mises-fisher-loss-for-training-sequence","slug":"von-mises-fisher-loss-for-training-sequence","title":"Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputs","date":"2018-12-10","arxiv_id":"1812.04616","n_code_links":1,"syntology":null},{"paper":null,"slug":"kernel-transformer-networks-for-compact","title":"Kernel Transformer Networks for Compact Spherical Convolution","date":"2018-12-07","arxiv_id":"1812.03115","n_code_links":0,"syntology":null},{"paper":null,"slug":"shufflenasnets-efficient-cnn-models-through","title":"ShuffleNASNets: Efficient CNN models through modified Efficient Neural Architecture Search","date":"2018-12-07","arxiv_id":"1812.02975","n_code_links":0,"syntology":null},{"paper":null,"slug":"dsnet-for-real-time-driving-scene-semantic","title":"DSNet for Real-Time Driving Scene Semantic Segmentation","date":"2018-12-06","arxiv_id":"1812.07049","n_code_links":0,"syntology":null},{"paper":null,"slug":"evaluating-architectural-choices-for-deep","title":"Evaluating Architectural Choices for Deep Learning Approaches for Question Answering over Knowledge Bases","date":"2018-12-06","arxiv_id":"1812.02536","n_code_links":0,"syntology":null},{"paper":null,"slug":"omnia-faster-r-cnn-detection-in-the-wild","title":"OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation","date":"2018-12-06","arxiv_id":"1812.02611","n_code_links":0,"syntology":null},{"paper":"/paper/online-model-distillation-for-efficient-video","slug":"online-model-distillation-for-efficient-video","title":"Online Model Distillation for Efficient Video Inference","date":"2018-12-06","arxiv_id":"1812.02699","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"the-ustc-nel-speech-translation-system-at","title":"The USTC-NEL Speech Translation system at IWSLT 2018","date":"2018-12-06","arxiv_id":"1812.02455","n_code_links":0,"syntology":null},{"paper":"/paper/video-action-transformer-network","slug":"video-action-transformer-network","title":"Video Action Transformer Network","date":"2018-12-06","arxiv_id":"1812.02707","n_code_links":0,"syntology":null},{"paper":"/paper/attending-to-mathematical-language-with","slug":"attending-to-mathematical-language-with","title":"Attending to Mathematical Language with Transformers","date":"2018-12-05","arxiv_id":"1812.02825","n_code_links":3,"syntology":null},{"paper":"/paper/generalized-zero-and-few-shot-learning-via","slug":"generalized-zero-and-few-shot-learning-via","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","date":"2018-12-05","arxiv_id":"1812.01784","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["edgarschnfld/CADA-VAE-PyTorch"],"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":["listed","official"]}}},{"paper":null,"slug":"channel-wise-pruning-of-neural-networks-with","title":"Channel-wise pruning of neural networks with tapering resource constraint","date":"2018-12-04","arxiv_id":"1812.07060","n_code_links":0,"syntology":null},{"paper":"/paper/practical-text-classification-with-large-pre","slug":"practical-text-classification-with-large-pre","title":"Practical Text Classification With Large Pre-Trained Language Models","date":"2018-12-04","arxiv_id":"1812.01207","n_code_links":1,"syntology":null},{"paper":"/paper/building-sequential-inference-models-for-end","slug":"building-sequential-inference-models-for-end","title":"Building Sequential Inference Models for End-to-End Response Selection","date":"2018-12-03","arxiv_id":"1812.00686","n_code_links":1,"syntology":null},{"paper":null,"slug":"identification-and-recognition-of-rice","title":"Identification and Recognition of Rice Diseases and Pests Using Convolutional Neural Networks","date":"2018-12-03","arxiv_id":"1812.01043","n_code_links":0,"syntology":null},{"paper":"/paper/deep-cosine-metric-learning-for-person-re","slug":"deep-cosine-metric-learning-for-person-re","title":"Deep Cosine Metric Learning for Person Re-Identification","date":"2018-12-02","arxiv_id":"1812.00442","n_code_links":5,"syntology":{"ran":7,"of":10,"n_ran_checked":7,"n_instrument":0,"unverified":3,"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) · 3 unverified","official":{"repos":["nwojke/cosine_metric_learning"],"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/revisiting-the-softmax-bellman-operator","slug":"revisiting-the-softmax-bellman-operator","title":"Revisiting the Softmax Bellman Operator: New Benefits and New Perspective","date":"2018-12-02","arxiv_id":"1812.00456","n_code_links":2,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"0 ran · 1 unverified","official":{"repos":["zhao-song/Softmax-DQN"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"paper":null,"slug":"effects-of-loss-functions-and-target","title":"Effects of Loss Functions And Target Representations on Adversarial Robustness","date":"2018-12-01","arxiv_id":"1812.00181","n_code_links":0,"syntology":null},{"paper":null,"slug":"glomo-unsupervised-learning-of-transferable","title":"GLoMo: Unsupervised Learning of Transferable Relational Graphs","date":"2018-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"layer-wise-coordination-between-encoder-and","title":"Layer-Wise Coordination between Encoder and Decoder for Neural Machine Translation","date":"2018-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-roi-transformer-for-detecting","slug":"learning-roi-transformer-for-detecting","title":"Learning RoI Transformer for Detecting Oriented Objects in Aerial Images","date":"2018-12-01","arxiv_id":"1812.00155","n_code_links":1,"syntology":{"ran":10,"of":11,"n_ran_checked":5,"n_instrument":5,"unverified":1,"pointer_only":11,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/pelee-a-real-time-object-detection-system-on-1","slug":"pelee-a-real-time-object-detection-system-on-1","title":"Pelee: A Real-Time Object Detection System on Mobile Devices","date":"2018-12-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"why-so-gloomy-a-bayesian-explanation-of-human","title":"Why so gloomy? A Bayesian explanation of human pessimism bias in the multi-armed bandit task","date":"2018-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/graph-based-global-reasoning-networks","slug":"graph-based-global-reasoning-networks","title":"Graph-Based Global Reasoning Networks","date":"2018-11-30","arxiv_id":"1811.12814","n_code_links":9,"syntology":{"ran":15,"of":15,"n_ran_checked":10,"n_instrument":5,"unverified":0,"pointer_only":7,"phrase":"15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/GloRe"],"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":"mixed-precision-quantization-of-convnets-via","title":"Mixed Precision Quantization of ConvNets via Differentiable Neural Architecture Search","date":"2018-11-30","arxiv_id":"1812.00090","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-monte-carlo-tree-search-as-a","title":"Using Monte Carlo Tree Search as a Demonstrator within Asynchronous Deep RL","date":"2018-11-30","arxiv_id":"1812.00045","n_code_links":0,"syntology":null},{"paper":"/paper/apollocar3d-a-large-3d-car-instance","slug":"apollocar3d-a-large-3d-car-instance","title":"ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving","date":"2018-11-29","arxiv_id":"1811.12222","n_code_links":0,"syntology":null},{"paper":null,"slug":"effective-fast-and-memory-efficient","title":"Effective, Fast, and Memory-Efficient Compressed Multi-function Convolutional Neural Networks for More Accurate Medical Image Classification","date":"2018-11-29","arxiv_id":"1811.11996","n_code_links":0,"syntology":null},{"paper":"/paper/grid-r-cnn","slug":"grid-r-cnn","title":"Grid R-CNN","date":"2018-11-29","arxiv_id":"1811.12030","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/tuplemax-loss-for-language-identification","slug":"tuplemax-loss-for-language-identification","title":"Tuplemax Loss for Language Identification","date":"2018-11-29","arxiv_id":"1811.12290","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-regionlets-blended-representation-and","title":"Deep Regionlets: Blended Representation and Deep Learning for Generic Object Detection","date":"2018-11-28","arxiv_id":"1811.11318","n_code_links":0,"syntology":null},{"paper":"/paper/espnetv2-a-light-weight-power-efficient-and","slug":"espnetv2-a-light-weight-power-efficient-and","title":"ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network","date":"2018-11-28","arxiv_id":"1811.11431","n_code_links":10,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sacmehta/EdgeNets"],"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/few-shot-generalization-across-dialogue-tasks","slug":"few-shot-generalization-across-dialogue-tasks","title":"Few-Shot Generalization Across Dialogue Tasks","date":"2018-11-28","arxiv_id":"1811.11707","n_code_links":2,"syntology":null},{"paper":"/paper/one-shot-instance-segmentation","slug":"one-shot-instance-segmentation","title":"One-Shot Instance Segmentation","date":"2018-11-28","arxiv_id":"1811.11507","n_code_links":3,"syntology":{"ran":3,"of":6,"n_ran_checked":3,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"3 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; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["bethgelab/siamese-mask-rcnn"],"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/strike-with-a-pose-neural-networks-are-easily","slug":"strike-with-a-pose-neural-networks-are-easily","title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","date":"2018-11-28","arxiv_id":"1811.11553","n_code_links":1,"syntology":null},{"paper":"/paper/deformable-convnets-v2-more-deformable-better","slug":"deformable-convnets-v2-more-deformable-better","title":"Deformable ConvNets v2: More Deformable, Better Results","date":"2018-11-27","arxiv_id":"1811.11168","n_code_links":26,"syntology":{"ran":10,"of":13,"n_ran_checked":9,"n_instrument":1,"unverified":3,"pointer_only":4,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/dense-xunit-networks","slug":"dense-xunit-networks","title":"Dense xUnit Networks","date":"2018-11-27","arxiv_id":"1811.11051","n_code_links":1,"syntology":null},{"paper":null,"slug":"generating-attention-from-classifier","title":"Generating Attention from Classifier Activations for Fine-grained Recognition","date":"2018-11-27","arxiv_id":"1811.10770","n_code_links":0,"syntology":null},{"paper":"/paper/grammars-and-reinforcement-learning-for","slug":"grammars-and-reinforcement-learning-for","title":"Grammars and reinforcement learning for molecule optimization","date":"2018-11-27","arxiv_id":"1811.11222","n_code_links":1,"syntology":null},{"paper":"/paper/iterative-transformer-network-for-3d-point","slug":"iterative-transformer-network-for-3d-point","title":"Iterative Transformer Network for 3D Point Cloud","date":"2018-11-27","arxiv_id":"1811.11209","n_code_links":1,"syntology":null},{"paper":"/paper/single-agent-policy-tree-search-with","slug":"single-agent-policy-tree-search-with","title":"Single-Agent Policy Tree Search With Guarantees","date":"2018-11-27","arxiv_id":"1811.10928","n_code_links":1,"syntology":null},{"paper":"/paper/instanas-instance-aware-neural-architecture","slug":"instanas-instance-aware-neural-architecture","title":"InstaNAS: Instance-aware Neural Architecture Search","date":"2018-11-26","arxiv_id":"1811.10201","n_code_links":2,"syntology":null},{"paper":null,"slug":"stacked-spatio-temporal-graph-convolutional","title":"Stacked Spatio-Temporal Graph Convolutional Networks for Action Segmentation","date":"2018-11-26","arxiv_id":"1811.10575","n_code_links":0,"syntology":null},{"paper":null,"slug":"non-local-roi-for-cross-object-perception","title":"Non-local RoI for Cross-Object Perception","date":"2018-11-25","arxiv_id":"1811.10002","n_code_links":0,"syntology":null},{"paper":null,"slug":"defect-detection-from-uav-images-based-on","title":"Defect Detection from UAV Images based on Region-Based CNNs","date":"2018-11-23","arxiv_id":"1811.09473","n_code_links":0,"syntology":null},{"paper":null,"slug":"natural-language-understanding-for-task","title":"Natural language understanding for task oriented dialog in the biomedical domain in a low resources context","date":"2018-11-23","arxiv_id":"1811.09417","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-brain-lesion-segmentation-from","title":"Unsupervised brain lesion segmentation from MRI using a convolutional autoencoder","date":"2018-11-23","arxiv_id":"1811.09655","n_code_links":0,"syntology":null},{"paper":"/paper/distorting-neural-representations-to-generate","slug":"distorting-neural-representations-to-generate","title":"Task-generalizable Adversarial Attack based on Perceptual Metric","date":"2018-11-22","arxiv_id":"1811.09020","n_code_links":1,"syntology":null},{"paper":"/paper/mask-r-cnn-with-pyramid-attention-network-for","slug":"mask-r-cnn-with-pyramid-attention-network-for","title":"Mask R-CNN with Pyramid Attention Network for Scene Text Detection","date":"2018-11-22","arxiv_id":"1811.09058","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-the-softmax-output-is-misleading-for","title":"How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples","date":"2018-11-21","arxiv_id":"1811.08577","n_code_links":0,"syntology":null},{"paper":"/paper/artificial-color-constancy-via-googlenet-with","slug":"artificial-color-constancy-via-googlenet-with","title":"Artificial Color Constancy via GoogLeNet with Angular Loss Function","date":"2018-11-20","arxiv_id":"1811.08456","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-better-features-for-face-detection","title":"Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision","date":"2018-11-20","arxiv_id":"1811.08557","n_code_links":0,"syntology":null},{"paper":null,"slug":"single-label-multi-class-image-classification","title":"Single-Label Multi-Class Image Classification by Deep Logistic Regression","date":"2018-11-20","arxiv_id":"1811.08400","n_code_links":0,"syntology":null},{"paper":null,"slug":"west-word-encoded-sequence-transducers","title":"WEST: Word Encoded Sequence Transducers","date":"2018-11-20","arxiv_id":"1811.08417","n_code_links":0,"syntology":null},{"paper":null,"slug":"do-normalization-layers-in-a-deep-convnet","title":"Do Normalization Layers in a Deep ConvNet Really Need to Be Distinct?","date":"2018-11-19","arxiv_id":"1811.07727","n_code_links":0,"syntology":null},{"paper":null,"slug":"fotonnet-a-hw-efficient-object-detection","title":"FotonNet: A HW-Efficient Object Detection System Using 3D-Depth Segmentation and 2D-DNN Classifier","date":"2018-11-19","arxiv_id":"1811.07493","n_code_links":0,"syntology":null},{"paper":null,"slug":"orthoseg-a-deep-multimodal-convolutional","title":"OrthoSeg: A Deep Multimodal Convolutional Neural Network for Semantic Segmentation of Orthoimagery","date":"2018-11-19","arxiv_id":"1811.07859","n_code_links":0,"syntology":null},{"paper":"/paper/glstylenet-higher-quality-style-transfer","slug":"glstylenet-higher-quality-style-transfer","title":"GLStyleNet: Higher Quality Style Transfer Combining Global and Local Pyramid Features","date":"2018-11-18","arxiv_id":"1811.07260","n_code_links":1,"syntology":null},{"paper":null,"slug":"multimodal-densenet","title":"Multimodal Densenet","date":"2018-11-18","arxiv_id":"1811.07407","n_code_links":0,"syntology":null},{"paper":"/paper/open-vocabulary-phrase-detection","slug":"open-vocabulary-phrase-detection","title":"Revisiting Image-Language Networks for Open-ended Phrase Detection","date":"2018-11-17","arxiv_id":"1811.07212","n_code_links":3,"syntology":null},{"paper":null,"slug":"composite-binary-decomposition-networks","title":"Composite Binary Decomposition Networks","date":"2018-11-16","arxiv_id":"1811.06668","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-efficient-graph-embedding-learning-for","title":"Data-Efficient Graph Embedding Learning for PCB Component Detection","date":"2018-11-16","arxiv_id":"1811.06994","n_code_links":0,"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":"/paper/residual-convolutional-neural-network","slug":"residual-convolutional-neural-network","title":"Residual Convolutional Neural Network Revisited with Active Weighted Mapping","date":"2018-11-16","arxiv_id":"1811.06878","n_code_links":1,"syntology":null},{"paper":null,"slug":"mathematical-analysis-of-adversarial-attacks","title":"Mathematical Analysis of Adversarial Attacks","date":"2018-11-15","arxiv_id":"1811.06492","n_code_links":0,"syntology":null},{"paper":null,"slug":"extractive-summary-as-discrete-latent","title":"Extractive Summary as Discrete Latent Variables","date":"2018-11-14","arxiv_id":"1811.05542","n_code_links":0,"syntology":null},{"paper":null,"slug":"quenn-quantization-engine-for-low-power","title":"QUENN: QUantization Engine for low-power Neural Networks","date":"2018-11-14","arxiv_id":"1811.05896","n_code_links":0,"syntology":null},{"paper":null,"slug":"application-of-faster-r-cnn-model-on-human","title":"Application of Faster R-CNN model on Human Running Pattern Recognition","date":"2018-11-13","arxiv_id":"1811.05147","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/m2det-a-single-shot-object-detector-based-on","slug":"m2det-a-single-shot-object-detector-based-on","title":"M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network","date":"2018-11-12","arxiv_id":"1811.04533","n_code_links":11,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"syntax-helps-elmo-understand-semantics-is","title":"Syntax Helps ELMo Understand Semantics: Is Syntax Still Relevant in a Deep Neural Architecture for SRL?","date":"2018-11-12","arxiv_id":"1811.04773","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-convergence-theory-for-deep-learning-via","title":"A Convergence Theory for Deep Learning via Over-Parameterization","date":"2018-11-09","arxiv_id":"1811.03962","n_code_links":0,"syntology":null},{"paper":"/paper/biologically-plausible-learning-algorithms","slug":"biologically-plausible-learning-algorithms","title":"Biologically-plausible learning algorithms can scale to large datasets","date":"2018-11-08","arxiv_id":"1811.03567","n_code_links":2,"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":null,"slug":"a-unified-framework-of-dnn-weight-pruning-and","title":"A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM","date":"2018-11-05","arxiv_id":"1811.01907","n_code_links":0,"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/you-only-search-once-single-shot-neural","slug":"you-only-search-once-single-shot-neural","title":"You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimization","date":"2018-11-05","arxiv_id":"1811.01567","n_code_links":1,"syntology":null},{"paper":null,"slug":"closed-form-variational-objectives-for","title":"Closed Form Variational Objectives For Bayesian Neural Networks with a Single Hidden Layer","date":"2018-11-02","arxiv_id":"1811.00686","n_code_links":0,"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":"bi-gans-st-for-perceptual-image-super","title":"Bi-GANs-ST for Perceptual Image Super-resolution","date":"2018-11-01","arxiv_id":"1811.00367","n_code_links":0,"syntology":null},{"paper":null,"slug":"dilated-densenets-for-relational-reasoning","title":"Dilated DenseNets for Relational Reasoning","date":"2018-11-01","arxiv_id":"1811.00410","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":null,"slug":"improving-adversarial-robustness-by","title":"Improving Adversarial Robustness by Encouraging Discriminative Features","date":"2018-11-01","arxiv_id":"1811.00621","n_code_links":0,"syntology":null},{"paper":null,"slug":"introduction-to-the-1st-place-winning-model","title":"Introduction to the 1st Place Winning Model of OpenImages Relationship Detection Challenge","date":"2018-11-01","arxiv_id":"1811.00662","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-modeling-teaches-you-more-than","title":"Language Modeling Teaches You More than Translation Does: Lessons Learned Through Auxiliary Syntactic Task Analysis","date":"2018-11-01","arxiv_id":null,"n_code_links":0,"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":null,"slug":"cross-lingual-transfer-learning-for","title":"Cross-Lingual Transfer Learning for Multilingual Task Oriented Dialog","date":"2018-10-31","arxiv_id":"1810.13327","n_code_links":0,"syntology":null}],"record_sha256":"a75613dbadb69ea4ba631d212567177e87e41d31efb8c9040ff263940cb0b941","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}