{"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/relu/papers/72","list_of":"/method/relu","method":"ReLU","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":72,"pages_in_order":104,"rows_per_page":100,"rows":[7101,7200],"of":10350,"counts":{"archive_papers_tagged":10350,"with_a_code_link":4256,"where_syntology_ran_a_sample":1079,"not_listed_spam_title":0,"listed":10350,"listed_where_code_ran":1079,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":909,"every_run_a_failure_of_syntologys_instrument":170,"listed_with_a_run_with_no_instrument_failure":909,"listed_every_run_a_failure_of_syntologys_instrument":170,"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/relu","prev":"/method/relu/papers/71","next":"/method/relu/papers/73","papers":[{"paper":null,"slug":"comparing-different-deep-learning","title":"Comparing Different Deep Learning Architectures for Classification of Chest Radiographs","date":"2020-02-20","arxiv_id":"2002.08991","n_code_links":0,"syntology":null},{"paper":"/paper/deep-fusion-of-local-and-non-local-features","slug":"deep-fusion-of-local-and-non-local-features","title":"Deep Fusion of Local and Non-Local Features for Precision Landslide Recognition","date":"2020-02-20","arxiv_id":"2002.08547","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-learning-estimation-of-multi-tissue","title":"Deep Learning Estimation of Multi-Tissue Constrained Spherical Deconvolution with Limited Single Shell DW-MRI","date":"2020-02-20","arxiv_id":"2002.08820","n_code_links":0,"syntology":null},{"paper":"/paper/maxup-a-simple-way-to-improve-generalization","slug":"maxup-a-simple-way-to-improve-generalization","title":"MaxUp: A Simple Way to Improve Generalization of Neural Network Training","date":"2020-02-20","arxiv_id":"2002.09024","n_code_links":1,"syntology":{"ran":0,"of":1,"n_ran_checked":0,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"0 ran · 1 unverified","official":null}},{"paper":null,"slug":"on-the-decision-boundaries-of-deep-neural-1","title":"On the Decision Boundaries of Neural Networks: A Tropical Geometry Perspective","date":"2020-02-20","arxiv_id":"2002.08838","n_code_links":0,"syntology":null},{"paper":"/paper/compressing-bert-studying-the-effects-of-1","slug":"compressing-bert-studying-the-effects-of-1","title":"Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning","date":"2020-02-19","arxiv_id":"2002.08307","n_code_links":1,"syntology":null},{"paper":"/paper/defraudnetend2end-fingerprint-spoof-detection","slug":"defraudnetend2end-fingerprint-spoof-detection","title":"DeFraudNet:End2End Fingerprint Spoof Detection using Patch Level Attention","date":"2020-02-19","arxiv_id":"2002.08214","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-tuning-u-net-for-ultrasound-image","title":"Fine tuning U-Net for ultrasound image segmentation: which layers?","date":"2020-02-19","arxiv_id":"2002.08438","n_code_links":0,"syntology":null},{"paper":"/paper/knapsack-pruning-with-inner-distillation","slug":"knapsack-pruning-with-inner-distillation","title":"Knapsack Pruning with Inner Distillation","date":"2020-02-19","arxiv_id":"2002.08258","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["yoniaflalo/knapsack_pruning"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/lambert-layout-aware-language-modeling-using","slug":"lambert-layout-aware-language-modeling-using","title":"LAMBERT: Layout-Aware (Language) Modeling for information extraction","date":"2020-02-19","arxiv_id":"2002.08087","n_code_links":1,"syntology":null},{"paper":"/paper/modelling-response-to-trypophobia-trigger","slug":"modelling-response-to-trypophobia-trigger","title":"Modelling response to trypophobia trigger using intermediate layers of ImageNet networks","date":"2020-02-19","arxiv_id":"2002.08490","n_code_links":1,"syntology":null},{"paper":"/paper/molecule-attention-transformer","slug":"molecule-attention-transformer","title":"Molecule Attention Transformer","date":"2020-02-19","arxiv_id":"2002.08264","n_code_links":7,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["gmum/MAT"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":"/paper/nnoculation-broad-spectrum-and-targeted","slug":"nnoculation-broad-spectrum-and-targeted","title":"NNoculation: Catching BadNets in the Wild","date":"2020-02-19","arxiv_id":"2002.08313","n_code_links":1,"syntology":null},{"paper":"/paper/toward-making-the-most-of-context-in-neural","slug":"toward-making-the-most-of-context-in-neural","title":"Towards Making the Most of Context in Neural Machine Translation","date":"2020-02-19","arxiv_id":"2002.07982","n_code_links":1,"syntology":null},{"paper":null,"slug":"tree-structured-attention-with-hierarchical-1","title":"Tree-structured Attention with Hierarchical Accumulation","date":"2020-02-19","arxiv_id":"2002.08046","n_code_links":0,"syntology":null},{"paper":null,"slug":"automated-cardiothoracic-ratio-calculation","title":"Automated Cardiothoracic Ratio Calculation and Cardiomegaly Detection using Deep Learning Approach","date":"2020-02-18","arxiv_id":"2002.07468","n_code_links":0,"syntology":null},{"paper":null,"slug":"conditional-self-attention-for-query-based","title":"Conditional Self-Attention for Query-based Summarization","date":"2020-02-18","arxiv_id":"2002.07338","n_code_links":0,"syntology":null},{"paper":"/paper/gradient-based-adversarial-training-on","slug":"gradient-based-adversarial-training-on","title":"Gradient-Based Adversarial Training on Transformer Networks for Detecting Check-Worthy Factual Claims","date":"2020-02-18","arxiv_id":"2002.07725","n_code_links":1,"syntology":null},{"paper":"/paper/hierarchical-transformer-network-for","slug":"hierarchical-transformer-network-for","title":"Hierarchical Transformer Network for Utterance-level Emotion Recognition","date":"2020-02-18","arxiv_id":"2002.07551","n_code_links":0,"syntology":null},{"paper":"/paper/picking-winning-tickets-before-training-by-1","slug":"picking-winning-tickets-before-training-by-1","title":"Picking Winning Tickets Before Training by Preserving Gradient Flow","date":"2020-02-18","arxiv_id":"2002.07376","n_code_links":3,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["alecwangcq/GraSP"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/sequential-latent-knowledge-selection-for-1","slug":"sequential-latent-knowledge-selection-for-1","title":"Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue","date":"2020-02-18","arxiv_id":"2002.07510","n_code_links":3,"syntology":{"ran":0,"of":5,"n_ran_checked":0,"n_instrument":0,"unverified":5,"pointer_only":5,"phrase":"0 ran · 5 unverified","official":{"repos":["bckim92/sequential-knowledge-transformer"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/uncertainty-in-structured-prediction","slug":"uncertainty-in-structured-prediction","title":"Uncertainty Estimation in Autoregressive Structured Prediction","date":"2020-02-18","arxiv_id":"2002.07650","n_code_links":1,"syntology":null},{"paper":"/paper/v4d4d-convolutional-neural-networks-for-video","slug":"v4d4d-convolutional-neural-networks-for-video","title":"V4D:4D Convolutional Neural Networks for Video-level Representation Learning","date":"2020-02-18","arxiv_id":"2002.07442","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-financial-service-chatbot-based-on-deep","title":"A Financial Service Chatbot based on Deep Bidirectional Transformers","date":"2020-02-17","arxiv_id":"2003.04987","n_code_links":0,"syntology":null},{"paper":null,"slug":"adaptive-experience-selection-for-policy","title":"Adaptive Experience Selection for Policy Gradient","date":"2020-02-17","arxiv_id":"2002.06946","n_code_links":0,"syntology":null},{"paper":null,"slug":"controlling-computation-versus-quality-for","title":"Controlling Computation versus Quality for Neural Sequence Models","date":"2020-02-17","arxiv_id":"2002.07106","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolutionary-optimization-of-deep-learning","title":"Evolutionary Optimization of Deep Learning Activation Functions","date":"2020-02-17","arxiv_id":"2002.07224","n_code_links":0,"syntology":null},{"paper":"/paper/identifying-critical-neurons-in-ann","slug":"identifying-critical-neurons-in-ann","title":"Identifying Critical Neurons in ANN Architectures using Mixed Integer Programming","date":"2020-02-17","arxiv_id":"2002.07259","n_code_links":1,"syntology":null},{"paper":"/paper/learning-architectures-for-binary-networks","slug":"learning-architectures-for-binary-networks","title":"Learning Architectures for Binary Networks","date":"2020-02-17","arxiv_id":"2002.06963","n_code_links":1,"syntology":null},{"paper":null,"slug":"low-rank-bottleneck-in-multi-head-attention","title":"Low-Rank Bottleneck in Multi-head Attention Models","date":"2020-02-17","arxiv_id":"2002.07028","n_code_links":0,"syntology":null},{"paper":"/paper/precision-gating-improving-neural-network-1","slug":"precision-gating-improving-neural-network-1","title":"Precision Gating: Improving Neural Network Efficiency with Dynamic Dual-Precision Activations","date":"2020-02-17","arxiv_id":"2002.07136","n_code_links":1,"syntology":{"ran":9,"of":11,"n_ran_checked":9,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"9 ran (of which 8 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["cornell-zhang/dnn-gating"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":8,"n_ran_no_instrument_failure":9,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"unsupervised-image-generation-enhanced","title":"Unsupervised Image-generation Enhanced Adaptation for Object Detection in Thermal images","date":"2020-02-17","arxiv_id":"2002.06770","n_code_links":0,"syntology":null},{"paper":"/paper/active-bayesian-assessment-for-black-box","slug":"active-bayesian-assessment-for-black-box","title":"Active Bayesian Assessment for Black-Box Classifiers","date":"2020-02-16","arxiv_id":"2002.06532","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["disiji/bayesian-blackbox"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/analytic-marching-an-analytic-meshing","slug":"analytic-marching-an-analytic-meshing","title":"Analytic Marching: An Analytic Meshing Solution from Deep Implicit Surface Networks","date":"2020-02-16","arxiv_id":"2002.06597","n_code_links":1,"syntology":null},{"paper":null,"slug":"generator-from-edges-reconstruction-of-facial","title":"Generator From Edges: Reconstruction of Facial Images","date":"2020-02-16","arxiv_id":"2002.06682","n_code_links":0,"syntology":null},{"paper":"/paper/multi-layer-representation-fusion-for-neural-2","slug":"multi-layer-representation-fusion-for-neural-2","title":"Multi-layer Representation Fusion for Neural Machine Translation","date":"2020-02-16","arxiv_id":"2002.06714","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"multi-task-siamese-neural-network-for","title":"Multi-Task Siamese Neural Network for Improving Replay Attack Detection","date":"2020-02-16","arxiv_id":"2002.07629","n_code_links":0,"syntology":null},{"paper":"/paper/neural-machine-translation-with-joint","slug":"neural-machine-translation-with-joint","title":"Neural Machine Translation with Joint Representation","date":"2020-02-16","arxiv_id":"2002.06546","n_code_links":1,"syntology":null},{"paper":null,"slug":"over-parameterized-adversarial-training-an","title":"Over-parameterized Adversarial Training: An Analysis Overcoming the Curse of Dimensionality","date":"2020-02-16","arxiv_id":"2002.06668","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatic-lesion-segmentation-and","title":"Automatic lesion segmentation and Pathological Myopia classification in fundus images","date":"2020-02-15","arxiv_id":"2002.06382","n_code_links":0,"syntology":null},{"paper":null,"slug":"many-to-many-voice-conversion-using","title":"Many-to-Many Voice Conversion using Conditional Cycle-Consistent Adversarial Networks","date":"2020-02-15","arxiv_id":"2002.06328","n_code_links":0,"syntology":null},{"paper":null,"slug":"small-energy-masking-for-improved-neural","title":"Small energy masking for improved neural network training for end-to-end speech recognition","date":"2020-02-15","arxiv_id":"2002.06312","n_code_links":0,"syntology":null},{"paper":"/paper/univilm-a-unified-video-and-language-pre","slug":"univilm-a-unified-video-and-language-pre","title":"UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation","date":"2020-02-15","arxiv_id":"2002.06353","n_code_links":2,"syntology":{"ran":1,"of":4,"n_ran_checked":0,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["microsoft/UniVL"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"deep-attentive-study-session-dropout","title":"Deep Attentive Study Session Dropout Prediction in Mobile Learning Environment","date":"2020-02-14","arxiv_id":"2002.11624","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-speaker-embeddings-for-far-field-speaker","title":"Deep Speaker Embeddings for Far-Field Speaker Recognition on Short Utterances","date":"2020-02-14","arxiv_id":"2002.06033","n_code_links":0,"syntology":null},{"paper":"/paper/gsanet-semantic-segmentation-with-global-and","slug":"gsanet-semantic-segmentation-with-global-and","title":"GSANet: Semantic Segmentation with Global and Selective Attention","date":"2020-02-14","arxiv_id":"2003.00830","n_code_links":0,"syntology":null},{"paper":null,"slug":"semi2i-semantically-consistent-image-to-image","title":"SemI2I: Semantically Consistent Image-to-Image Translation for Domain Adaptation of Remote Sensing Data","date":"2020-02-14","arxiv_id":"2002.05925","n_code_links":0,"syntology":null},{"paper":"/paper/skip-connections-matter-on-the","slug":"skip-connections-matter-on-the","title":"Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets","date":"2020-02-14","arxiv_id":"2002.05990","n_code_links":4,"syntology":{"ran":4,"of":9,"n_ran_checked":1,"n_instrument":3,"unverified":5,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 5 unverified","official":{"repos":["csdongxian/skip-connections-matter"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"stress-test-evaluation-of-transformer-based","title":"Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks","date":"2020-02-14","arxiv_id":"2002.06261","n_code_links":0,"syntology":null},{"paper":"/paper/towards-an-appropriate-query-key-and-value","slug":"towards-an-appropriate-query-key-and-value","title":"Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing","date":"2020-02-14","arxiv_id":"2002.07033","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":2,"n_instrument":1,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/transformer-on-a-diet","slug":"transformer-on-a-diet","title":"Transformer on a Diet","date":"2020-02-14","arxiv_id":"2002.06170","n_code_links":1,"syntology":null},{"paper":"/paper/a-simple-framework-for-contrastive-learning","slug":"a-simple-framework-for-contrastive-learning","title":"A Simple Framework for Contrastive Learning of Visual Representations","date":"2020-02-13","arxiv_id":"2002.05709","n_code_links":96,"syntology":{"ran":115,"of":137,"n_ran_checked":90,"n_instrument":25,"unverified":22,"pointer_only":52,"phrase":"115 ran (of which 33 constructed an object rather than computing a result; 90 with no instrument failure: 1 honoured, 1 violated, 88 with no contract checked; 25 where Syntology's instrument failed) · 22 unverified","official":{"repos":["google-research/simclr"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/cross-iteration-batch-normalization","slug":"cross-iteration-batch-normalization","title":"Cross-Iteration Batch Normalization","date":"2020-02-13","arxiv_id":"2002.05712","n_code_links":2,"syntology":{"ran":4,"of":6,"n_ran_checked":4,"n_instrument":0,"unverified":2,"pointer_only":1,"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) · 2 unverified","official":{"repos":["Howal/Cross-iterationBatchNorm"],"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/endol2h-deep-super-resolution-for-capsule","slug":"endol2h-deep-super-resolution-for-capsule","title":"EndoL2H: Deep Super-Resolution for Capsule Endoscopy","date":"2020-02-13","arxiv_id":"2002.05459","n_code_links":3,"syntology":null},{"paper":null,"slug":"object-detection-on-single-monocular-images","title":"Object Detection on Single Monocular Images through Canonical Correlation Analysis","date":"2020-02-13","arxiv_id":"2002.05349","n_code_links":0,"syntology":null},{"paper":"/paper/pcsgan-perceptual-cyclic-synthesized","slug":"pcsgan-perceptual-cyclic-synthesized","title":"PCSGAN: Perceptual Cyclic-Synthesized Generative Adversarial Networks for Thermal and NIR to Visible Image Transformation","date":"2020-02-13","arxiv_id":"2002.07082","n_code_links":1,"syntology":null},{"paper":"/paper/physical-accuracy-of-deep-neural-networks-for","slug":"physical-accuracy-of-deep-neural-networks-for","title":"Physical Accuracy of Deep Neural Networks for 2D and 3D Multi-Mineral Segmentation of Rock micro-CT Images","date":"2020-02-13","arxiv_id":"2002.05322","n_code_links":1,"syntology":null},{"paper":"/paper/sparse-and-structured-visual-attention-1","slug":"sparse-and-structured-visual-attention-1","title":"Sparse and Structured Visual Attention","date":"2020-02-13","arxiv_id":"2002.05556","n_code_links":1,"syntology":null},{"paper":"/paper/spotnet-self-attention-multi-task-network-for","slug":"spotnet-self-attention-multi-task-network-for","title":"SpotNet: Self-Attention Multi-Task Network for Object Detection","date":"2020-02-13","arxiv_id":"2002.05540","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-use-of-convolutional-neural-networks-for","title":"The use of Convolutional Neural Networks for signal-background classification in Particle Physics experiments","date":"2020-02-13","arxiv_id":"2002.05761","n_code_links":0,"syntology":null},{"paper":"/paper/attentional-speech-recognition-models","slug":"attentional-speech-recognition-models","title":"Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances","date":"2020-02-12","arxiv_id":"2002.05150","n_code_links":1,"syntology":null},{"paper":"/paper/end-to-end-face-parsing-via-interlinked","slug":"end-to-end-face-parsing-via-interlinked","title":"End-to-End Face Parsing via Interlinked Convolutional Neural Networks","date":"2020-02-12","arxiv_id":"2002.04831","n_code_links":1,"syntology":null},{"paper":"/paper/glu-variants-improve-transformer","slug":"glu-variants-improve-transformer","title":"GLU Variants Improve Transformer","date":"2020-02-12","arxiv_id":"2002.05202","n_code_links":27,"syntology":{"ran":9,"of":9,"n_ran_checked":7,"n_instrument":2,"unverified":0,"pointer_only":7,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 3 honoured, 4 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/lookahead-a-far-sighted-alternative-of-1","slug":"lookahead-a-far-sighted-alternative-of-1","title":"Lookahead: a Far-Sighted Alternative of Magnitude-based Pruning","date":"2020-02-12","arxiv_id":"2002.04809","n_code_links":1,"syntology":{"ran":8,"of":10,"n_ran_checked":6,"n_instrument":2,"unverified":2,"pointer_only":10,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 6 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["alinlab/lookahead_pruning"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/on-layer-normalization-in-the-transformer-1","slug":"on-layer-normalization-in-the-transformer-1","title":"On Layer Normalization in the Transformer Architecture","date":"2020-02-12","arxiv_id":"2002.04745","n_code_links":9,"syntology":{"ran":10,"of":11,"n_ran_checked":10,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/real-or-not-real-that-is-the-question-1","slug":"real-or-not-real-that-is-the-question-1","title":"Real or Not Real, that is the Question","date":"2020-02-12","arxiv_id":"2002.05512","n_code_links":2,"syntology":null},{"paper":null,"slug":"understanding-global-loss-landscape-of-one","title":"Understanding Global Loss Landscape of One-hidden-layer ReLU Networks, Part 1: Theory","date":"2020-02-12","arxiv_id":"2002.04763","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-novel-and-efficient-tumor-detection","title":"A Novel and Efficient Tumor Detection Framework for Pancreatic Cancer via CT Images","date":"2020-02-11","arxiv_id":"2002.04493","n_code_links":0,"syntology":null},{"paper":null,"slug":"best-of-both-worlds-automl-codesign-of-a-cnn","title":"Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator","date":"2020-02-11","arxiv_id":"2002.05022","n_code_links":0,"syntology":null},{"paper":null,"slug":"goldilocks-neural-networks","title":"Goldilocks Neural Networks","date":"2020-02-11","arxiv_id":"2002.05059","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-bias-of-gradient-descent-for-wide","slug":"implicit-bias-of-gradient-descent-for-wide","title":"Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss","date":"2020-02-11","arxiv_id":"2002.04486","n_code_links":1,"syntology":null},{"paper":null,"slug":"improved-consistency-regularization-for-gans","title":"Improved Consistency Regularization for GANs","date":"2020-02-11","arxiv_id":"2002.04724","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-transfer-learning-model-for-binary","title":"Optimal Transfer Learning Model for Binary Classification of Funduscopic Images through Simple Heuristics","date":"2020-02-11","arxiv_id":"2002.04189","n_code_links":0,"syntology":null},{"paper":null,"slug":"superbloom-bloom-filter-meets-transformer-1","title":"Superbloom: Bloom filter meets Transformer","date":"2020-02-11","arxiv_id":"2002.04723","n_code_links":0,"syntology":null},{"paper":"/paper/the-devil-is-in-the-channels-mutual-channel","slug":"the-devil-is-in-the-channels-mutual-channel","title":"The Devil is in the Channels: Mutual-Channel Loss for Fine-Grained Image Classification","date":"2020-02-11","arxiv_id":"2002.04264","n_code_links":3,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":2,"phrase":"4 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; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["dongliangchang/Mutual-Channel-Loss"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"training-with-streaming-annotation","title":"Training with Streaming Annotation","date":"2020-02-11","arxiv_id":"2002.04165","n_code_links":0,"syntology":null},{"paper":"/paper/vision-based-fight-detection-from","slug":"vision-based-fight-detection-from","title":"Vision-based Fight Detection from Surveillance Cameras","date":"2020-02-11","arxiv_id":"2002.04355","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-gated-networks-a-framework-to-understand","title":"Deep Gated Networks: A framework to understand training and generalisation in deep learning","date":"2020-02-10","arxiv_id":"2002.03996","n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-representation-learning-for-dynamical","title":"Deep Representation Learning for Dynamical Systems Modeling","date":"2020-02-10","arxiv_id":"2002.05111","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-multi-speaker-speech-recognition-1","title":"End-to-End Multi-speaker Speech Recognition with Transformer","date":"2020-02-10","arxiv_id":"2002.03921","n_code_links":0,"syntology":null},{"paper":"/paper/how-well-do-u-net-based-segmentation-trained","slug":"how-well-do-u-net-based-segmentation-trained","title":"How well do U-Net-based segmentation trained on adult cardiac magnetic resonance imaging data generalise to rare congenital heart diseases for surgical planning?","date":"2020-02-10","arxiv_id":"2002.04392","n_code_links":2,"syntology":null},{"paper":null,"slug":"on-approximation-capabilities-of-relu","title":"On Approximation Capabilities of ReLU Activation and Softmax Output Layer in Neural Networks","date":"2020-02-10","arxiv_id":"2002.04060","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-complexity-of-finding-stationary-points-of","title":"Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions","date":"2020-02-10","arxiv_id":"2002.04130","n_code_links":0,"syntology":null},{"paper":null,"slug":"outlier-guided-optimization-of-abdominal","title":"Outlier Guided Optimization of Abdominal Segmentation","date":"2020-02-10","arxiv_id":"2002.04098","n_code_links":0,"syntology":null},{"paper":"/paper/polynomial-optimization-for-bounding","slug":"polynomial-optimization-for-bounding","title":"Semialgebraic Optimization for Lipschitz Constants of ReLU Networks","date":"2020-02-10","arxiv_id":"2002.03657","n_code_links":2,"syntology":null},{"paper":null,"slug":"pre-training-tasks-for-embedding-based-large","title":"Pre-training Tasks for Embedding-based Large-scale Retrieval","date":"2020-02-10","arxiv_id":"2002.03932","n_code_links":0,"syntology":null},{"paper":null,"slug":"statistical-guarantees-of-generative","title":"Distribution Approximation and Statistical Estimation Guarantees of Generative Adversarial Networks","date":"2020-02-10","arxiv_id":"2002.03938","n_code_links":0,"syntology":null},{"paper":null,"slug":"stickypillars-robust-feature-matching-on","title":"StickyPillars: Robust and Efficient Feature Matching on Point Clouds using Graph Neural Networks","date":"2020-02-10","arxiv_id":"2002.03983","n_code_links":0,"syntology":null},{"paper":null,"slug":"validation-and-optimization-of-multi-organ","title":"Validation and Optimization of Multi-Organ Segmentation on Clinical Imaging Archives","date":"2020-02-10","arxiv_id":"2002.04102","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-learning-approach-to-automate-high","title":"A Deep Learning Approach to Automate High-Resolution Blood Vessel Reconstruction on Computerized Tomography Images With or Without the Use of Contrast Agent","date":"2020-02-09","arxiv_id":"2002.03463","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-neural-network-pruning-using","title":"Convolutional Neural Network Pruning Using Filter Attenuation","date":"2020-02-09","arxiv_id":"2002.03299","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-distance-between-two-neural-networks","slug":"on-the-distance-between-two-neural-networks","title":"On the distance between two neural networks and the stability of learning","date":"2020-02-09","arxiv_id":"2002.03432","n_code_links":2,"syntology":null},{"paper":null,"slug":"bitpruning-learning-bitlengths-for-aggressive","title":"BitPruning: Learning Bitlengths for Aggressive and Accurate Quantization","date":"2020-02-08","arxiv_id":"2002.03090","n_code_links":0,"syntology":null},{"paper":"/paper/blank-language-models","slug":"blank-language-models","title":"Blank Language Models","date":"2020-02-08","arxiv_id":"2002.03079","n_code_links":1,"syntology":{"ran":7,"of":8,"n_ran_checked":7,"n_instrument":0,"unverified":1,"pointer_only":1,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["Varal7/blank_language_model"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/soft-threshold-weight-reparameterization-for","slug":"soft-threshold-weight-reparameterization-for","title":"Soft Threshold Weight Reparameterization for Learnable Sparsity","date":"2020-02-08","arxiv_id":"2002.03231","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"1 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["RAIVNLab/STR"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/cifar-10-image-classification-using-feature","slug":"cifar-10-image-classification-using-feature","title":"CIFAR-10 Image Classification Using Feature Ensembles","date":"2020-02-07","arxiv_id":"2002.03846","n_code_links":1,"syntology":null},{"paper":"/paper/image-fine-grained-inpainting","slug":"image-fine-grained-inpainting","title":"Image Fine-grained Inpainting","date":"2020-02-07","arxiv_id":"2002.02609","n_code_links":3,"syntology":null},{"paper":null,"slug":"learning-hyperspectral-feature-extraction-and","title":"Learning Hyperspectral Feature Extraction and Classification with ResNeXt Network","date":"2020-02-07","arxiv_id":"2002.02585","n_code_links":0,"syntology":null},{"paper":null,"slug":"multimodal-matching-transformer-for-live","title":"Multimodal Matching Transformer for Live Commenting","date":"2020-02-07","arxiv_id":"2002.02649","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-capsule-model-for-intent","slug":"transformer-capsule-model-for-intent","title":"Transformer-Capsule Model for Intent Detection","date":"2020-02-07","arxiv_id":null,"n_code_links":0,"syntology":null}],"record_sha256":"7724edc623e85b1272e083ff36131283712e8d3e4475c582b9b34f2963a1ea00","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}