{"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/86","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":86,"pages_in_order":104,"rows_per_page":100,"rows":[8501,8600],"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/85","next":"/method/relu/papers/87","papers":[{"paper":"/paper/story-ending-prediction-by-transferable-bert","slug":"story-ending-prediction-by-transferable-bert","title":"Story Ending Prediction by Transferable BERT","date":"2019-05-17","arxiv_id":"1905.07504","n_code_links":1,"syntology":null},{"paper":"/paper/190506596","slug":"190506596","title":"Joint Source-Target Self Attention with Locality Constraints","date":"2019-05-16","arxiv_id":"1905.06596","n_code_links":2,"syntology":null},{"paper":"/paper/deep-compressed-sensing","slug":"deep-compressed-sensing","title":"Deep Compressed Sensing","date":"2019-05-16","arxiv_id":"1905.06723","n_code_links":1,"syntology":null},{"paper":"/paper/deep-learning-for-interference-identification","slug":"deep-learning-for-interference-identification","title":"Deep Learning for Interference Identification: Band, Training SNR, and Sample Selection","date":"2019-05-16","arxiv_id":"1905.08054","n_code_links":1,"syntology":null},{"paper":null,"slug":"gated-convolutional-neural-networks-for","title":"Gated Convolutional Neural Networks for Domain Adaptation","date":"2019-05-16","arxiv_id":"1905.06906","n_code_links":0,"syntology":null},{"paper":"/paper/hibert-document-level-pre-training-of","slug":"hibert-document-level-pre-training-of","title":"HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization","date":"2019-05-16","arxiv_id":"1905.06566","n_code_links":0,"syntology":null},{"paper":null,"slug":"latent-universal-task-specific-bert","title":"Latent Universal Task-Specific BERT","date":"2019-05-16","arxiv_id":"1905.06638","n_code_links":0,"syntology":null},{"paper":null,"slug":"trk-cnn-transferable-ranking-cnn-for-image","title":"TRk-CNN: Transferable Ranking-CNN for image classification of glaucoma, glaucoma suspect, and normal eyes","date":"2019-05-16","arxiv_id":"1905.06509","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-deep-learning-based-approach-for-fast-and","title":"A deep-learning-based approach for fast and robust steel surface defects classification","date":"2019-05-15","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/behavior-sequence-transformer-for-e-commerce","slug":"behavior-sequence-transformer-for-e-commerce","title":"Behavior Sequence Transformer for E-commerce Recommendation in Alibaba","date":"2019-05-15","arxiv_id":"1905.06874","n_code_links":9,"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":null}},{"paper":null,"slug":"dynamic-neural-network-channel-execution-for","title":"Dynamic Neural Network Channel Execution for Efficient Training","date":"2019-05-15","arxiv_id":"1905.06435","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-based-single-step-quantitative","title":"Learning-based Single-step Quantitative Susceptibility Mapping Reconstruction Without Brain Extraction","date":"2019-05-15","arxiv_id":"1905.05953","n_code_links":0,"syntology":null},{"paper":"/paper/online-normalization-for-training-neural","slug":"online-normalization-for-training-neural","title":"Online Normalization for Training Neural Networks","date":"2019-05-15","arxiv_id":"1905.05894","n_code_links":1,"syntology":{"ran":9,"of":16,"n_ran_checked":9,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"9 ran (of which 0 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) · 7 unverified","official":{"repos":["cerebras/online-normalization"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":"/paper/rethinking-the-usage-of-batch-normalization","slug":"rethinking-the-usage-of-batch-normalization","title":"Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks","date":"2019-05-15","arxiv_id":"1905.05928","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":"/paper/190505621","slug":"190505621","title":"Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation","date":"2019-05-14","arxiv_id":"1905.05621","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 ran (of which 2 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":["fastnlp/nlp-dataset","fastnlp/style-transformer"],"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/190505661","slug":"190505661","title":"Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images","date":"2019-05-14","arxiv_id":"1905.05661","n_code_links":3,"syntology":null},{"paper":null,"slug":"190508610","title":"Skin Cancer Recognition using Deep Residual Network","date":"2019-05-14","arxiv_id":"1905.08610","n_code_links":0,"syntology":null},{"paper":"/paper/american-sign-language-alphabet-recognition","slug":"american-sign-language-alphabet-recognition","title":"American Sign Language Alphabet Recognition using Deep Learning","date":"2019-05-14","arxiv_id":"1905.05487","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-recognition-system-for-recognizing","title":"End to End Recognition System for Recognizing Offline Unconstrained Vietnamese Handwriting","date":"2019-05-14","arxiv_id":"1905.05381","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-groove-with-inverse-sequence","slug":"learning-to-groove-with-inverse-sequence","title":"Learning to Groove with Inverse Sequence Transformations","date":"2019-05-14","arxiv_id":"1905.06118","n_code_links":1,"syntology":null},{"paper":null,"slug":"190508606","title":"VGG Fine-tuning for Cooking State Recognition","date":"2019-05-13","arxiv_id":"1905.08606","n_code_links":0,"syntology":null},{"paper":null,"slug":"almost-unsupervised-text-to-speech-and","title":"Almost Unsupervised Text to Speech and Automatic Speech Recognition","date":"2019-05-13","arxiv_id":"1905.06791","n_code_links":0,"syntology":null},{"paper":"/paper/cutmix-regularization-strategy-to-train","slug":"cutmix-regularization-strategy-to-train","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","date":"2019-05-13","arxiv_id":"1905.04899","n_code_links":30,"syntology":{"ran":17,"of":24,"n_ran_checked":11,"n_instrument":6,"unverified":7,"pointer_only":5,"phrase":"17 ran (of which 6 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 0 violated, 9 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified","official":{"repos":["clovaai/CutMix-PyTorch"],"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":"implicit-filter-sparsification-in","title":"Implicit Filter Sparsification In Convolutional Neural Networks","date":"2019-05-13","arxiv_id":"1905.04967","n_code_links":0,"syntology":null},{"paper":"/paper/synchronous-bidirectional-neural-machine","slug":"synchronous-bidirectional-neural-machine","title":"Synchronous Bidirectional Neural Machine Translation","date":"2019-05-13","arxiv_id":"1905.04847","n_code_links":2,"syntology":null},{"paper":null,"slug":"towards-a-regularity-theory-for-relu-networks","title":"Towards a regularity theory for ReLU networks -- chain rule and global error estimates","date":"2019-05-13","arxiv_id":"1905.04992","n_code_links":0,"syntology":null},{"paper":"/paper/weakly-supervised-caricature-face-parsing","slug":"weakly-supervised-caricature-face-parsing","title":"Weakly-supervised Caricature Face Parsing through Domain Adaptation","date":"2019-05-13","arxiv_id":"1905.05091","n_code_links":1,"syntology":null},{"paper":null,"slug":"structure-from-articulated-motion-an-accurate","title":"Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data","date":"2019-05-12","arxiv_id":"1905.04789","n_code_links":0,"syntology":null},{"paper":null,"slug":"cyclone-intensity-estimate-with-context-aware","title":"Cyclone intensity estimate with context-aware cyclegan","date":"2019-05-11","arxiv_id":"1905.04425","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-robotic-manipulation-through-visual","title":"Learning Robotic Manipulation through Visual Planning and Acting","date":"2019-05-11","arxiv_id":"1905.04411","n_code_links":0,"syntology":null},{"paper":"/paper/linear-range-in-gradient-descent","slug":"linear-range-in-gradient-descent","title":"Linear Range in Gradient Descent","date":"2019-05-11","arxiv_id":"1905.04561","n_code_links":1,"syntology":null},{"paper":null,"slug":"190504307","title":"Semantic Segmentation of Seismic Images","date":"2019-05-10","arxiv_id":"1905.04307","n_code_links":0,"syntology":null},{"paper":null,"slug":"densifying-assumed-sparse-tensors-improving","title":"Densifying Assumed-sparse Tensors: Improving Memory Efficiency and MPI Collective Performance during Tensor Accumulation for Parallelized Training of Neural Machine Translation Models","date":"2019-05-10","arxiv_id":"1905.04035","n_code_links":0,"syntology":null},{"paper":null,"slug":"language-modeling-with-deep-transformers","title":"Language Modeling with Deep Transformers","date":"2019-05-10","arxiv_id":"1905.04226","n_code_links":0,"syntology":null},{"paper":"/paper/region-attention-networks-for-pose-and","slug":"region-attention-networks-for-pose-and","title":"Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition","date":"2019-05-10","arxiv_id":"1905.04075","n_code_links":1,"syntology":null},{"paper":null,"slug":"t-net-encoder-decoder-in-encoder-decoder","title":"T-Net: Nested encoder-decoder architecture for the main vessel segmentation in coronary angiography","date":"2019-05-10","arxiv_id":"1905.04197","n_code_links":0,"syntology":null},{"paper":"/paper/using-syntactical-and-logical-forms-to","slug":"using-syntactical-and-logical-forms-to","title":"A logical-based corpus for cross-lingual evaluation","date":"2019-05-10","arxiv_id":"1905.05704","n_code_links":1,"syntology":null},{"paper":"/paper/190503670","slug":"190503670","title":"S4L: Self-Supervised Semi-Supervised Learning","date":"2019-05-09","arxiv_id":"1905.03670","n_code_links":1,"syntology":{"ran":14,"of":19,"n_ran_checked":14,"n_instrument":0,"unverified":5,"pointer_only":19,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":"/paper/190503678","slug":"190503678","title":"What Do Single-view 3D Reconstruction Networks Learn?","date":"2019-05-09","arxiv_id":"1905.03678","n_code_links":0,"syntology":null},{"paper":null,"slug":"190503288","title":"Advancements in Image Classification using Convolutional Neural Network","date":"2019-05-08","arxiv_id":"1905.03288","n_code_links":0,"syntology":null},{"paper":null,"slug":"190503356","title":"QSMGAN: Improved Quantitative Susceptibility Mapping using 3D Generative Adversarial Networks with Increased Receptive Field","date":"2019-05-08","arxiv_id":"1905.03356","n_code_links":0,"syntology":null},{"paper":"/paper/190503381","slug":"190503381","title":"AutoAssist: A Framework to Accelerate Training of Deep Neural Networks","date":"2019-05-08","arxiv_id":"1905.03381","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"multi-task-human-analysis-in-still-images","title":"Multi-task human analysis in still images: 2D/3D pose, depth map, and multi-part segmentation","date":"2019-05-08","arxiv_id":"1905.03003","n_code_links":0,"syntology":null},{"paper":null,"slug":"photometric-transformer-networks-and-label","title":"Photometric Transformer Networks and Label Adjustment for Breast Density Prediction","date":"2019-05-08","arxiv_id":"1905.02906","n_code_links":0,"syntology":null},{"paper":"/paper/rwth-asr-systems-for-librispeech-hybrid-vs","slug":"rwth-asr-systems-for-librispeech-hybrid-vs","title":"RWTH ASR Systems for LibriSpeech: Hybrid vs Attention -- w/o Data Augmentation","date":"2019-05-08","arxiv_id":"1905.03072","n_code_links":2,"syntology":null},{"paper":"/paper/unified-language-model-pre-training-for","slug":"unified-language-model-pre-training-for","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","date":"2019-05-08","arxiv_id":"1905.03197","n_code_links":9,"syntology":null},{"paper":null,"slug":"ensemble-of-convolutional-neural-networks","title":"Ensemble of Convolutional Neural Networks Trained with Different Activation Functions","date":"2019-05-07","arxiv_id":"1905.02473","n_code_links":0,"syntology":null},{"paper":"/paper/pog-personalized-outfit-generation-for","slug":"pog-personalized-outfit-generation-for","title":"POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashion","date":"2019-05-06","arxiv_id":"1905.01866","n_code_links":1,"syntology":null},{"paper":"/paper/searching-for-mobilenetv3","slug":"searching-for-mobilenetv3","title":"Searching for MobileNetV3","date":"2019-05-06","arxiv_id":"1905.02244","n_code_links":67,"syntology":{"ran":86,"of":105,"n_ran_checked":75,"n_instrument":11,"unverified":19,"pointer_only":46,"phrase":"86 ran (of which 22 constructed an object rather than computing a result; 75 with no instrument failure: 6 honoured, 2 violated, 67 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified","official":null}},{"paper":null,"slug":"nonlinear-approximation-and-deep-relu","title":"Nonlinear Approximation and (Deep) ReLU Networks","date":"2019-05-05","arxiv_id":"1905.02199","n_code_links":0,"syntology":null},{"paper":null,"slug":"sinreq-generalized-sinusoidal-regularization","title":"SinReQ: Generalized Sinusoidal Regularization for Low-Bitwidth Deep Quantized Training","date":"2019-05-04","arxiv_id":"1905.01416","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximation-spaces-of-deep-neural-networks","title":"Approximation spaces of deep neural networks","date":"2019-05-03","arxiv_id":"1905.01208","n_code_links":0,"syntology":null},{"paper":"/paper/brain-tumor-detection-using-convolutional","slug":"brain-tumor-detection-using-convolutional","title":"Brain Tumor Detection using Convolutional Neural Network","date":"2019-05-03","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":"/paper/deep-residual-reinforcement-learning","slug":"deep-residual-reinforcement-learning","title":"Deep Residual Reinforcement Learning","date":"2019-05-03","arxiv_id":"1905.01072","n_code_links":1,"syntology":null},{"paper":null,"slug":"effectiveness-of-self-normalizing-neural","title":"Effectiveness of Self Normalizing Neural Networks for Text Classification","date":"2019-05-03","arxiv_id":"1905.01338","n_code_links":0,"syntology":null},{"paper":null,"slug":"static-activation-function-normalization","title":"Static Activation Function Normalization","date":"2019-05-03","arxiv_id":"1905.01369","n_code_links":0,"syntology":null},{"paper":null,"slug":"190503709","title":"Visualizing the Consequences of Climate Change Using Cycle-Consistent Adversarial Networks","date":"2019-05-02","arxiv_id":"1905.03709","n_code_links":0,"syntology":null},{"paper":"/paper/billion-scale-semi-supervised-learning-for","slug":"billion-scale-semi-supervised-learning-for","title":"Billion-scale semi-supervised learning for image classification","date":"2019-05-02","arxiv_id":"1905.00546","n_code_links":4,"syntology":null},{"paper":"/paper/collaborative-evolutionary-reinforcement","slug":"collaborative-evolutionary-reinforcement","title":"Collaborative Evolutionary Reinforcement Learning","date":"2019-05-02","arxiv_id":"1905.00976","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":5,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"5 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; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["intelai/cerl"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"directing-dnns-attention-for-facial","title":"Directing DNNs Attention for Facial Attribution Classification using Gradient-weighted Class Activation Mapping","date":"2019-05-02","arxiv_id":"1905.00593","n_code_links":0,"syntology":null},{"paper":"/paper/omni-scale-feature-learning-for-person-re","slug":"omni-scale-feature-learning-for-person-re","title":"Omni-Scale Feature Learning for Person Re-Identification","date":"2019-05-02","arxiv_id":"1905.00953","n_code_links":17,"syntology":{"ran":14,"of":26,"n_ran_checked":12,"n_instrument":2,"unverified":12,"pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 2 where Syntology's instrument failed) · 12 unverified","official":{"repos":["KaiyangZhou/deep-person-reid"],"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":"toward-extremely-low-bit-and-lossless","title":"Toward Extremely Low Bit and Lossless Accuracy in DNNs with Progressive ADMM","date":"2019-05-02","arxiv_id":"1905.00789","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-theoretical-framework-for-deep-and-locally","title":"A theoretical framework for deep and locally connected ReLU network","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"aligning-artificial-neural-networks-to-the","title":"Aligning Artificial Neural Networks to the Brain yields Shallow Recurrent Architectures","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"bnn-improved-binary-network-training-1","title":"BNN+: Improved Binary Network Training","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cem-rl-combining-evolutionary-and-gradient","title":"CEM-RL: Combining evolutionary and gradient-based methods for policy search","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"complexity-of-training-relu-neural-networks","title":"Complexity of Training ReLU Neural Networks","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cutting-down-training-memory-by-re-fowarding-1","title":"Cutting Down Training Memory by Re-fowarding","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dana-scalable-out-of-the-box-distributed-asgd","title":"DANA: Scalable Out-of-the-box Distributed ASGD Without Retuning","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deep-denoising-rate-optimal-recovery-of-1","title":"Deep Denoising: Rate-Optimal Recovery of Structured Signals with a Deep Prior","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"deli-fisher-gan-stable-and-efficient-image","title":"Deli-Fisher GAN: Stable and Efficient Image Generation With Structured Latent Generative Space","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"detecting-out-of-distribution-samples-using","title":"Detecting Out-Of-Distribution Samples Using Low-Order Deep Features Statistics","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/discourse-representation-structure-parsing-1","slug":"discourse-representation-structure-parsing-1","title":"Discourse Representation Structure Parsing with Recurrent Neural Networks and the Transformer Model","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/fast-autoaugment","slug":"fast-autoaugment","title":"Fast AutoAugment","date":"2019-05-01","arxiv_id":"1905.00397","n_code_links":11,"syntology":{"ran":37,"of":40,"n_ran_checked":21,"n_instrument":16,"unverified":3,"pointer_only":7,"phrase":"37 ran (of which 2 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 0 violated, 21 with no contract checked; 16 where Syntology's instrument failed) · 3 unverified","official":{"repos":["kakaobrain/fast-autoaugment"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"feed-forward-propagation-in-probabilistic","title":"Feed-forward Propagation in Probabilistic Neural Networks with Categorical and Max Layers","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"g-sgd-optimizing-relu-neural-networks-in-its","title":"G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-transformer","title":"Graph Transformer","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ib-gan-disentangled-representation-learning","slug":"ib-gan-disentangled-representation-learning","title":"IB-GAN: Disentangled Representation Learning with Information Bottleneck GAN","date":"2019-05-01","arxiv_id":null,"n_code_links":2,"syntology":null},{"paper":null,"slug":"learning-agents-with-prioritization-and","title":"Learning agents with prioritization and parameter noise in continuous state and action space","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-search-efficient-densenet-with","title":"Learning to Search Efficient DenseNet with Layer-wise Pruning","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"manifoldnet-a-deep-neural-network-for","title":"MANIFOLDNET: A DEEP NEURAL NETWORK FOR MANIFOLD-VALUED DATA","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/multi-agent-dual-learning","slug":"multi-agent-dual-learning","title":"Multi-Agent Dual Learning","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-margin-theory-of-feedforward-neural-1","title":"On the Margin Theory of Feedforward Neural Networks","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-statistical-and-information","title":"On the Statistical and Information Theoretical Characteristics of DNN Representations","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"over-parameterization-improves-generalization","title":"Over-parameterization Improves Generalization in the XOR Detection Problem","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"robustness-and-equivariance-of-neural","title":"Robustness and Equivariance of Neural Networks","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"the-expressive-power-of-deep-neural-networks","title":"The Expressive Power of Deep Neural Networks with Circulant Matrices","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/the-role-of-over-parametrization-in","slug":"the-role-of-over-parametrization-in","title":"The role of over-parametrization in generalization of neural networks","date":"2019-05-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"total-style-transfer-with-a-single-feed","title":"Total Style Transfer with a Single Feed-Forward Network","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-a-better-understanding-of-vector","title":"Towards a better understanding of Vector Quantized Autoencoders","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"traditional-and-heavy-tailed-self-1","title":"Traditional and Heavy Tailed Self Regularization in Neural Network Models","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-xl-language-modeling-with-longer","title":"Transformer-XL: Language Modeling with Longer-Term Dependency","date":"2019-05-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/object-contour-and-edge-detection-with","slug":"object-contour-and-edge-detection-with","title":"Object Contour and Edge Detection with RefineContourNet","date":"2019-04-30","arxiv_id":"1904.13353","n_code_links":2,"syntology":null},{"paper":null,"slug":"resnet-can-be-pruned-60x-introducing-network","title":"ResNet Can Be Pruned 60x: Introducing Network Purification and Unused Path Removal (P-RM) after Weight Pruning","date":"2019-04-30","arxiv_id":"1905.00136","n_code_links":0,"syntology":null},{"paper":null,"slug":"very-deep-self-attention-networks-for-end-to","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","date":"2019-04-30","arxiv_id":"1904.13377","n_code_links":0,"syntology":null},{"paper":"/paper/190503696","slug":"190503696","title":"HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision","date":"2019-04-29","arxiv_id":"1905.03696","n_code_links":1,"syntology":{"ran":1,"of":3,"n_ran_checked":0,"n_instrument":1,"unverified":2,"pointer_only":3,"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":["zhen-dong/hawq"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["unlocated"]}}},{"paper":"/paper/learning-raw-image-denoising-with-bayer","slug":"learning-raw-image-denoising-with-bayer","title":"Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation","date":"2019-04-29","arxiv_id":"1904.12945","n_code_links":1,"syntology":null},{"paper":null,"slug":"optical-transient-object-classification-in","title":"Optical Transient Object Classification in Wide Field Small Aperture Telescopes with Neural Networks","date":"2019-04-29","arxiv_id":"1904.12987","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-data-augmentation-1","slug":"unsupervised-data-augmentation-1","title":"Unsupervised Data Augmentation for Consistency Training","date":"2019-04-29","arxiv_id":"1904.12848","n_code_links":20,"syntology":{"ran":30,"of":52,"n_ran_checked":22,"n_instrument":8,"unverified":22,"pointer_only":17,"phrase":"30 ran (of which 3 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 8 where Syntology's instrument failed) · 22 unverified","official":{"repos":["google-research/uda"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":14,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"softmax-optimizations-for-intel-xeon","title":"Softmax Optimizations for Intel Xeon Processor-based Platforms","date":"2019-04-28","arxiv_id":"1904.12380","n_code_links":0,"syntology":null}],"record_sha256":"43e2aa59706f3b2610862a10345d789c70539aae2f6e6deec8bf59fe1c8da957","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}