{"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/dropout/papers/267","list_of":"/method/dropout","method":"Dropout","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":267,"pages_in_order":275,"rows_per_page":100,"rows":[26601,26700],"of":27472,"counts":{"archive_papers_tagged":27472,"with_a_code_link":12129,"where_syntology_ran_a_sample":3620,"not_listed_spam_title":0,"listed":27472,"listed_where_code_ran":3620,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3044,"every_run_a_failure_of_syntologys_instrument":576,"listed_with_a_run_with_no_instrument_failure":3044,"listed_every_run_a_failure_of_syntologys_instrument":576,"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/dropout","prev":"/method/dropout/papers/266","next":"/method/dropout/papers/268","papers":[{"paper":"/paper/fbnet-hardware-aware-efficient-convnet-design","slug":"fbnet-hardware-aware-efficient-convnet-design","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","date":"2018-12-09","arxiv_id":"1812.03443","n_code_links":5,"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: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/mobile-vision"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"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":"prior-networks-for-detection-of-adversarial","title":"Prior Networks for Detection of Adversarial Attacks","date":"2018-12-06","arxiv_id":"1812.02575","n_code_links":0,"syntology":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/random-spiking-and-systematic-evaluation-of","slug":"random-spiking-and-systematic-evaluation-of","title":"Random Spiking and Systematic Evaluation of Defenses Against Adversarial Examples","date":"2018-12-05","arxiv_id":"1812.01804","n_code_links":1,"syntology":null},{"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":null,"slug":"inferring-remote-channel-state-information","title":"Inferring Remote Channel State Information: Cramér-Rao Lower Bound and Deep Learning Implementation","date":"2018-12-04","arxiv_id":"1812.01223","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":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":null,"slug":"network-compression-via-recursive-bayesian","title":"Accelerate CNN via Recursive Bayesian Pruning","date":"2018-12-02","arxiv_id":"1812.00353","n_code_links":0,"syntology":null},{"paper":"/paper/can-we-gain-more-from-orthogonality-1","slug":"can-we-gain-more-from-orthogonality-1","title":"Can We Gain More from Orthogonality Regularizations in Training Deep Networks?","date":"2018-12-01","arxiv_id":null,"n_code_links":1,"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":null,"slug":"stochastic-training-of-residual-networks-a","title":"Stochastic Training of Residual Networks: a Differential Equation Viewpoint","date":"2018-12-01","arxiv_id":"1812.00174","n_code_links":0,"syntology":null},{"paper":"/paper/evaluating-bayesian-deep-learning-methods-for","slug":"evaluating-bayesian-deep-learning-methods-for","title":"Evaluating Bayesian Deep Learning Methods for Semantic Segmentation","date":"2018-11-30","arxiv_id":"1811.12709","n_code_links":1,"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/improving-robustness-of-neural-dialog-systems","slug":"improving-robustness-of-neural-dialog-systems","title":"Improving Robustness of Neural Dialog Systems in a Data-Efficient Way with Turn Dropout","date":"2018-11-29","arxiv_id":"1811.12148","n_code_links":1,"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/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/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":"/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/probability-based-detection-quality-pdq-a","slug":"probability-based-detection-quality-pdq-a","title":"Probabilistic Object Detection: Definition and Evaluation","date":"2018-11-27","arxiv_id":"1811.10800","n_code_links":1,"syntology":{"ran":7,"of":7,"n_ran_checked":7,"n_instrument":0,"unverified":0,"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) · 0 unverified","official":null}},{"paper":null,"slug":"uncertainty-aware-multimodal-activity","title":"Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference","date":"2018-11-27","arxiv_id":"1811.10811","n_code_links":0,"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":"structured-pruning-of-neural-networks-with","title":"Structured Pruning of Neural Networks with Budget-Aware Regularization","date":"2018-11-23","arxiv_id":"1811.09332","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":"a-self-adaptive-network-for-multiple","title":"A Self-Adaptive Network For Multiple Sclerosis Lesion Segmentation From Multi-Contrast MRI With Various Imaging Protocols","date":"2018-11-19","arxiv_id":"1811.07491","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":"variational-bayesian-dropout","title":"Variational Bayesian Dropout with a Hierarchical Prior","date":"2018-11-19","arxiv_id":"1811.07533","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":null,"slug":"dropfilter-a-novel-regularization-method-for","title":"DropFilter: A Novel Regularization Method for Learning Convolutional Neural Networks","date":"2018-11-16","arxiv_id":"1811.06783","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":"distortion-robust-image-classification-using","title":"Distortion Robust Image Classification using Deep Convolutional Neural Network with Discrete Cosine Transform","date":"2018-11-14","arxiv_id":"1811.05819","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":"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":"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":null,"slug":"on-the-statistical-and-information-theoretic","title":"Statistical Characteristics of Deep Representations: An Empirical Investigation","date":"2018-11-08","arxiv_id":"1811.03666","n_code_links":0,"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":null,"slug":"a-batched-scalable-multi-objective-bayesian","title":"A Batched Scalable Multi-Objective Bayesian Optimization Algorithm","date":"2018-11-04","arxiv_id":"1811.01323","n_code_links":0,"syntology":null},{"paper":null,"slug":"radius-margin-bounds-for-deep-neural-networks","title":"Radius-margin bounds for deep neural networks","date":"2018-11-03","arxiv_id":"1811.01171","n_code_links":0,"syntology":null},{"paper":null,"slug":"analysing-dropout-and-compounding-errors-in","title":"Analysing Dropout and Compounding Errors in Neural Language Models","date":"2018-11-02","arxiv_id":"1811.00998","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":"/paper/argumentative-link-prediction-using-residual","slug":"argumentative-link-prediction-using-residual","title":"Argumentative Link Prediction using Residual Networks and Multi-Objective Learning","date":"2018-11-01","arxiv_id":null,"n_code_links":1,"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":"/paper/variational-dropout-via-empirical-bayes","slug":"variational-dropout-via-empirical-bayes","title":"Variational Dropout via Empirical Bayes","date":"2018-11-01","arxiv_id":"1811.00596","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":null,"slug":"performance-assessment-of-the-deep-learning","title":"Performance assessment of the deep learning technologies in grading glaucoma severity","date":"2018-10-31","arxiv_id":"1810.13376","n_code_links":0,"syntology":null},{"paper":null,"slug":"structure-learning-of-deep-neural-networks","title":"Structure Learning of Deep Neural Networks with Q-Learning","date":"2018-10-31","arxiv_id":"1810.13155","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-effect-of-learning-strategy-versus","title":"The Effect of Learning Strategy versus Inherent Architecture Properties on the Ability of Convolutional Neural Networks to Develop Transformation Invariance","date":"2018-10-31","arxiv_id":"1810.13128","n_code_links":0,"syntology":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":"/paper/dropblock-a-regularization-method-for","slug":"dropblock-a-regularization-method-for","title":"DropBlock: A regularization method for convolutional networks","date":"2018-10-30","arxiv_id":"1810.12890","n_code_links":10,"syntology":null},{"paper":"/paper/investigation-of-enhanced-tacotron-text-to","slug":"investigation-of-enhanced-tacotron-text-to","title":"Investigation of enhanced Tacotron text-to-speech synthesis systems with self-attention for pitch accent language","date":"2018-10-29","arxiv_id":"1810.11960","n_code_links":1,"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":"automatically-evolving-cnn-architectures","title":"Automatically Evolving CNN Architectures Based on Blocks","date":"2018-10-28","arxiv_id":"1810.11875","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-neural-networks-with-extra","title":"Convolutional neural networks with extra-classical receptive fields","date":"2018-10-27","arxiv_id":"1810.11594","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":"dropfilter-dropout-for-convolutions","title":"DropFilter: Dropout for Convolutions","date":"2018-10-23","arxiv_id":"1810.09849","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploration-of-dropout-with-rnns-for","title":"An Exploration of Dropout with RNNs for Natural Language Inference","date":"2018-10-22","arxiv_id":"1810.08606","n_code_links":0,"syntology":null},{"paper":"/paper/can-we-gain-more-from-orthogonality","slug":"can-we-gain-more-from-orthogonality","title":"Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?","date":"2018-10-22","arxiv_id":"1810.09102","n_code_links":1,"syntology":null},{"paper":null,"slug":"dermatologist-level-dermoscopy-skin-cancer","title":"Dermatologist Level Dermoscopy Skin Cancer Classification Using Different Deep Learning Convolutional Neural Networks Algorithms","date":"2018-10-21","arxiv_id":"1810.10348","n_code_links":0,"syntology":null},{"paper":"/paper/on-extensions-of-clever-a-neural-network","slug":"on-extensions-of-clever-a-neural-network","title":"On Extensions of CLEVER: A Neural Network Robustness Evaluation Algorithm","date":"2018-10-19","arxiv_id":"1810.08640","n_code_links":1,"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":"/paper/a-comparison-of-1-d-and-2-d-deep","slug":"a-comparison-of-1-d-and-2-d-deep","title":"A Comparison of 1-D and 2-D Deep Convolutional Neural Networks in ECG Classification","date":"2018-10-16","arxiv_id":"1810.07088","n_code_links":1,"syntology":null},{"paper":null,"slug":"fine-grained-classification-of-cervical-cells","title":"Fine-Grained Classification of Cervical Cells Using Morphological and Appearance Based Convolutional Neural Networks","date":"2018-10-14","arxiv_id":"1810.06058","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-relationship-between-dropout-and","slug":"on-the-relationship-between-dropout-and","title":"An ETF view of Dropout regularization","date":"2018-10-14","arxiv_id":"1810.06049","n_code_links":1,"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/convolutional-neural-networks-in-convolution","slug":"convolutional-neural-networks-in-convolution","title":"Convolutional Neural Networks In Convolution","date":"2018-10-09","arxiv_id":"1810.03946","n_code_links":1,"syntology":null},{"paper":"/paper/deepweeds-a-multiclass-weed-species-image","slug":"deepweeds-a-multiclass-weed-species-image","title":"DeepWeeds: A Multiclass Weed Species Image Dataset for Deep Learning","date":"2018-10-09","arxiv_id":"1810.05726","n_code_links":1,"syntology":{"ran":1,"of":2,"n_ran_checked":0,"n_instrument":1,"unverified":1,"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) · 1 unverified","official":{"repos":["AlexOlsen/DeepWeeds"],"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":["official"]}}},{"paper":null,"slug":"bootstrapped-cnns-for-building-segmentation","title":"Bootstrapped CNNs for Building Segmentation on RGB-D Aerial Imagery","date":"2018-10-08","arxiv_id":"1810.03570","n_code_links":0,"syntology":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":"/paper/on-breimans-dilemma-in-neural-networks-phase","slug":"on-breimans-dilemma-in-neural-networks-phase","title":"Rethinking Breiman's Dilemma in Neural Networks: Phase Transitions of Margin Dynamics","date":"2018-10-08","arxiv_id":"1810.03389","n_code_links":1,"syntology":null},{"paper":null,"slug":"optimization-algorithm-inspired-deep-neural","title":"Optimization Algorithm Inspired Deep Neural Network Structure Design","date":"2018-10-03","arxiv_id":"1810.01638","n_code_links":0,"syntology":null},{"paper":"/paper/implicit-self-regularization-in-deep-neural","slug":"implicit-self-regularization-in-deep-neural","title":"Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning","date":"2018-10-02","arxiv_id":"1810.01075","n_code_links":3,"syntology":null},{"paper":"/paper/nu-litenet-mobile-landmark-recognition-using","slug":"nu-litenet-mobile-landmark-recognition-using","title":"NU-LiteNet: Mobile Landmark Recognition using Convolutional Neural Networks","date":"2018-10-02","arxiv_id":"1810.01074","n_code_links":1,"syntology":null},{"paper":null,"slug":"super-resolution-via-conditional-implicit","title":"Super-Resolution via Conditional Implicit Maximum Likelihood Estimation","date":"2018-10-02","arxiv_id":"1810.01406","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":"/paper/adv-bnn-improved-adversarial-defense-through","slug":"adv-bnn-improved-adversarial-defense-through","title":"Adv-BNN: Improved Adversarial Defense through Robust Bayesian Neural Network","date":"2018-10-01","arxiv_id":"1810.01279","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":["xuanqing94/BayesianDefense"],"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":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":"/paper/bayesian-prediction-of-future-street-scenes-1","slug":"bayesian-prediction-of-future-street-scenes-1","title":"Bayesian Prediction of Future Street Scenes using Synthetic Likelihoods","date":"2018-10-01","arxiv_id":"1810.00746","n_code_links":1,"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}],"record_sha256":"5990c53ca8d66c3ffc8777e99d9fd68d4c160f96688cb6104f25c7d422becd5d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}