{"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/78","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":78,"pages_in_order":104,"rows_per_page":100,"rows":[7701,7800],"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/77","next":"/method/relu/papers/79","papers":[{"paper":"/paper/hubert-untangles-bert-to-improve-transfer-1","slug":"hubert-untangles-bert-to-improve-transfer-1","title":"HUBERT Untangles BERT to Improve Transfer across NLP Tasks","date":"2019-10-25","arxiv_id":"1910.12647","n_code_links":1,"syntology":null},{"paper":"/paper/mockingjay-unsupervised-speech-representation","slug":"mockingjay-unsupervised-speech-representation","title":"Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders","date":"2019-10-25","arxiv_id":"1910.12638","n_code_links":7,"syntology":{"ran":8,"of":11,"n_ran_checked":6,"n_instrument":2,"unverified":3,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","official":{"repos":["andi611/Self-Supervised-Speech-Pretraining-and-Representation-Learning"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/parallel-wavegan-a-fast-waveform-generation","slug":"parallel-wavegan-a-fast-waveform-generation","title":"Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram","date":"2019-10-25","arxiv_id":"1910.11480","n_code_links":12,"syntology":{"ran":17,"of":20,"n_ran_checked":17,"n_instrument":0,"unverified":3,"pointer_only":1,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"towards-online-end-to-end-transformer","title":"Towards Online End-to-end Transformer Automatic Speech Recognition","date":"2019-10-25","arxiv_id":"1910.11871","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-of-efficient-asr-rescoring","title":"An Empirical Study of Efficient ASR Rescoring with Transformers","date":"2019-10-24","arxiv_id":"1910.11450","n_code_links":0,"syntology":null},{"paper":null,"slug":"emotion-recognition-with-4kresolution","title":"Emotion recognition with 4kresolution database","date":"2019-10-24","arxiv_id":"1910.11276","n_code_links":0,"syntology":null},{"paper":"/paper/espnet-tts-unified-reproducible-and","slug":"espnet-tts-unified-reproducible-and","title":"ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit","date":"2019-10-24","arxiv_id":"1910.10909","n_code_links":3,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":1,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["r9y9/wavenet_vocoder","espnet/espnet"],"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","unlocated"]}}},{"paper":null,"slug":"promoting-the-knowledge-of-source-syntax-in","title":"Promoting the Knowledge of Source Syntax in Transformer NMT Is Not Needed","date":"2019-10-24","arxiv_id":"1910.11218","n_code_links":0,"syntology":null},{"paper":"/paper/u-time-a-fully-convolutional-network-for-time","slug":"u-time-a-fully-convolutional-network-for-time","title":"U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging","date":"2019-10-24","arxiv_id":"1910.11162","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":2,"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":null}},{"paper":null,"slug":"unified-multi-scale-feature-abstraction-for","title":"Unified Multi-scale Feature Abstraction for Medical Image Segmentation","date":"2019-10-24","arxiv_id":"1910.11456","n_code_links":0,"syntology":null},{"paper":"/paper/a-transformer-with-interleaved-self-attention","slug":"a-transformer-with-interleaved-self-attention","title":"A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Models","date":"2019-10-23","arxiv_id":"1910.10352","n_code_links":1,"syntology":null},{"paper":null,"slug":"controlling-the-output-length-of-neural","title":"Controlling the Output Length of Neural Machine Translation","date":"2019-10-23","arxiv_id":"1910.10408","n_code_links":0,"syntology":null},{"paper":null,"slug":"correction-of-automatic-speech-recognition","title":"Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Model","date":"2019-10-23","arxiv_id":"1910.10697","n_code_links":0,"syntology":null},{"paper":"/paper/deja-vu-double-feature-presentation-in-deep","slug":"deja-vu-double-feature-presentation-in-deep","title":"Deja-vu: Double Feature Presentation and Iterated Loss in Deep Transformer Networks","date":"2019-10-23","arxiv_id":"1910.10324","n_code_links":2,"syntology":null},{"paper":null,"slug":"identification-of-primary-angle-closure-on-as","title":"Identification of primary angle-closure on AS-OCT images with Convolutional Neural Networks","date":"2019-10-23","arxiv_id":"1910.10414","n_code_links":0,"syntology":null},{"paper":"/paper/neural-ordinary-differential-equations-for","slug":"neural-ordinary-differential-equations-for","title":"Neural Ordinary Differential Equations for Semantic Segmentation of Individual Colon Glands","date":"2019-10-23","arxiv_id":"1910.10470","n_code_links":2,"syntology":null},{"paper":null,"slug":"semantic-segmentation-of-skin-lesions-using-a","title":"Semantic Segmentation of Skin Lesions using a Small Data Set","date":"2019-10-23","arxiv_id":"1910.10534","n_code_links":0,"syntology":null},{"paper":null,"slug":"tct-a-cross-supervised-learning-method-for","title":"TCT: A Cross-supervised Learning Method for Multimodal Sequence Representation","date":"2019-10-23","arxiv_id":"1911.05186","n_code_links":0,"syntology":null},{"paper":"/paper/4-connected-shift-residual-networks","slug":"4-connected-shift-residual-networks","title":"4-Connected Shift Residual Networks","date":"2019-10-22","arxiv_id":"1910.09931","n_code_links":1,"syntology":null},{"paper":"/paper/complex-transformer-a-framework-for-modeling","slug":"complex-transformer-a-framework-for-modeling","title":"Complex Transformer: A Framework for Modeling Complex-Valued Sequence","date":"2019-10-22","arxiv_id":"1910.10202","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":4,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":{"repos":["muqiaoy/dl_signal"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/deep-set-to-set-matching-and-learning","slug":"deep-set-to-set-matching-and-learning","title":"Exchangeable deep neural networks for set-to-set matching and learning","date":"2019-10-22","arxiv_id":"1910.09972","n_code_links":2,"syntology":null},{"paper":null,"slug":"depth-adaptive-transformer","title":"Depth-Adaptive Transformer","date":"2019-10-22","arxiv_id":"1910.10073","n_code_links":0,"syntology":null},{"paper":"/paper/improving-siamese-networks-for-one-shot","slug":"improving-siamese-networks-for-one-shot","title":"Improving Siamese Networks for One Shot Learning using Kernel Based Activation functions","date":"2019-10-22","arxiv_id":"1910.09798","n_code_links":1,"syntology":null},{"paper":"/paper/improving-transformer-based-speech","slug":"improving-transformer-based-speech","title":"Improving Transformer-based Speech Recognition Using Unsupervised Pre-training","date":"2019-10-22","arxiv_id":"1910.09932","n_code_links":1,"syntology":null},{"paper":"/paper/self-correction-for-human-parsing","slug":"self-correction-for-human-parsing","title":"Self-Correction for Human Parsing","date":"2019-10-22","arxiv_id":"1910.09777","n_code_links":2,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 1 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["PeikeLi/Self-Correction-Human-Parsing"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"sequence-to-sequence-singing-synthesis-using","title":"Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer","date":"2019-10-22","arxiv_id":"1910.09989","n_code_links":0,"syntology":null},{"paper":null,"slug":"softgan-learning-generative-models","title":"CycleGAN Voice Conversion of Spectral Envelopes using Adversarial Weights","date":"2019-10-22","arxiv_id":"1910.12614","n_code_links":0,"syntology":null},{"paper":"/paper/transformer-based-acoustic-modeling-for","slug":"transformer-based-acoustic-modeling-for","title":"Transformer-based Acoustic Modeling for Hybrid Speech Recognition","date":"2019-10-22","arxiv_id":"1910.09799","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximation-capabilities-of-neural-networks","title":"Approximation capabilities of neural networks on unbounded domains","date":"2019-10-21","arxiv_id":"1910.09293","n_code_links":0,"syntology":null},{"paper":null,"slug":"depth-wise-decomposition-for-accelerating","title":"Depth-wise Decomposition for Accelerating Separable Convolutions in Efficient Convolutional Neural Networks","date":"2019-10-21","arxiv_id":"1910.09455","n_code_links":0,"syntology":null},{"paper":null,"slug":"directed-weighting-group-lasso-for-eltwise","title":"Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning","date":"2019-10-21","arxiv_id":"1910.09318","n_code_links":0,"syntology":null},{"paper":"/paper/improving-vehicle-re-identification-using-cnn","slug":"improving-vehicle-re-identification-using-cnn","title":"Improving Vehicle Re-Identification using CNN Latent Spaces: Metrics Comparison and Track-to-track Extension","date":"2019-10-21","arxiv_id":"1910.09458","n_code_links":1,"syntology":null},{"paper":null,"slug":"kuronet-pre-modern-japanese-kuzushiji","title":"KuroNet: Pre-Modern Japanese Kuzushiji Character Recognition with Deep Learning","date":"2019-10-21","arxiv_id":"1910.09433","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-make-generalizable-and-diverse","title":"Learning to Make Generalizable and Diverse Predictions for Retrosynthesis","date":"2019-10-21","arxiv_id":"1910.09688","n_code_links":0,"syntology":null},{"paper":"/paper/miscnn-a-framework-for-medical-image","slug":"miscnn-a-framework-for-medical-image","title":"MIScnn: A Framework for Medical Image Segmentation with Convolutional Neural Networks and Deep Learning","date":"2019-10-21","arxiv_id":"1910.09308","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-cnn-fast-and-reliable-tool-for","slug":"transformer-cnn-fast-and-reliable-tool-for","title":"Transformer-CNN: Fast and Reliable tool for QSAR","date":"2019-10-21","arxiv_id":"1911.06603","n_code_links":1,"syntology":null},{"paper":null,"slug":"universal-flow-approximation-with-deep","title":"On the space-time expressivity of ResNets","date":"2019-10-21","arxiv_id":"1910.09599","n_code_links":0,"syntology":null},{"paper":"/paper/deep-speech-inpainting-of-time-frequency","slug":"deep-speech-inpainting-of-time-frequency","title":"Deep speech inpainting of time-frequency masks","date":"2019-10-20","arxiv_id":"1910.09058","n_code_links":2,"syntology":null},{"paper":"/paper/image-difficulty-curriculum-for-generative","slug":"image-difficulty-curriculum-for-generative","title":"Image Difficulty Curriculum for Generative Adversarial Networks (CuGAN)","date":"2019-10-20","arxiv_id":"1910.08967","n_code_links":1,"syntology":null},{"paper":null,"slug":"mixmodule-mixed-cnn-kernel-module-for-medical","title":"MixModule: Mixed CNN Kernel Module for Medical Image Segmentation","date":"2019-10-19","arxiv_id":"1910.08728","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-aware-online-adversarial","slug":"spatial-aware-online-adversarial","title":"SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking","date":"2019-10-19","arxiv_id":"1910.08681","n_code_links":1,"syntology":null},{"paper":null,"slug":"tracking-assisted-segmentation-of-biological","title":"Tracking-Assisted Segmentation of Biological Cells","date":"2019-10-19","arxiv_id":"1910.08735","n_code_links":0,"syntology":null},{"paper":"/paper/bobby2-buffer-based-robust-high-speed-object","slug":"bobby2-buffer-based-robust-high-speed-object","title":"BOBBY2: Buffer Based Robust High-Speed Object Tracking","date":"2019-10-18","arxiv_id":"1910.08263","n_code_links":1,"syntology":null},{"paper":"/paper/intracranial-hemorrhage-segmentation-using","slug":"intracranial-hemorrhage-segmentation-using","title":"Intracranial Hemorrhage Segmentation Using Deep Convolutional Model","date":"2019-10-18","arxiv_id":"1910.08643","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":{"repos":["Murtadha44/-Intracranial-Hemorrhage-Segmentation-Using-Deep-Convolutional-Model-U-Net-"],"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":"/paper/surreal-complex-valued-deep-learning-as","slug":"surreal-complex-valued-deep-learning-as","title":"SurReal: Complex-Valued Learning as Principled Transformations on a Scaling and Rotation Manifold","date":"2019-10-18","arxiv_id":"1910.11334","n_code_links":1,"syntology":{"ran":4,"of":5,"n_ran_checked":3,"n_instrument":1,"unverified":1,"pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"towards-quantifying-intrinsic-generalization","title":"Towards Quantifying Intrinsic Generalization of Deep ReLU Networks","date":"2019-10-18","arxiv_id":"1910.08581","n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-quantized-transformer-for-improved","title":"Fully Quantized Transformer for Machine Translation","date":"2019-10-17","arxiv_id":"1910.10485","n_code_links":0,"syntology":null},{"paper":null,"slug":"predicting-retrosynthetic-pathways-using-a","title":"Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy","date":"2019-10-17","arxiv_id":"1910.08036","n_code_links":0,"syntology":null},{"paper":"/paper/question-classification-with-deep","slug":"question-classification-with-deep","title":"Question Classification with Deep Contextualized Transformer","date":"2019-10-17","arxiv_id":"1910.10492","n_code_links":1,"syntology":null},{"paper":null,"slug":"conservation-ai-live-stream-analysis-for-the","title":"Conservation AI: Live Stream Analysis for the Detection of Endangered Species Using Convolutional Neural Networks and Drone Technology","date":"2019-10-16","arxiv_id":"1910.07360","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficiency-through-auto-sizing-notre-dame","title":"Efficiency through Auto-Sizing: Notre Dame NLP's Submission to the WNGT 2019 Efficiency Task","date":"2019-10-16","arxiv_id":"1910.07134","n_code_links":0,"syntology":null},{"paper":null,"slug":"evolution-of-transfer-learning-in-natural","title":"Evolution of transfer learning in natural language processing","date":"2019-10-16","arxiv_id":"1910.07370","n_code_links":0,"syntology":null},{"paper":null,"slug":"hidden-unit-specialization-in-layered-neural","title":"Hidden Unit Specialization in Layered Neural Networks: ReLU vs. Sigmoidal Activation","date":"2019-10-16","arxiv_id":"1910.07476","n_code_links":0,"syntology":null},{"paper":null,"slug":"imperial-college-london-submission-to-vatex","title":"Imperial College London Submission to VATEX Video Captioning Task","date":"2019-10-16","arxiv_id":"1910.07482","n_code_links":0,"syntology":null},{"paper":"/paper/injecting-hierarchy-with-u-net-transformers","slug":"injecting-hierarchy-with-u-net-transformers","title":"Injecting Hierarchy with U-Net Transformers","date":"2019-10-16","arxiv_id":"1910.10488","n_code_links":2,"syntology":null},{"paper":null,"slug":"mix-review-alleviate-forgetting-in-the","title":"Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models","date":"2019-10-16","arxiv_id":"1910.07117","n_code_links":0,"syntology":null},{"paper":null,"slug":"offline-handwritten-mathematical-symbol","title":"Offline handwritten mathematical symbol recognition utilising deep learning","date":"2019-10-16","arxiv_id":"1910.07395","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-asr-with-contextual-block","title":"Transformer ASR with Contextual Block Processing","date":"2019-10-16","arxiv_id":"1910.07204","n_code_links":0,"syntology":null},{"paper":null,"slug":"using-whole-document-context-in-neural","title":"Using Whole Document Context in Neural Machine Translation","date":"2019-10-16","arxiv_id":"1910.07481","n_code_links":0,"syntology":null},{"paper":null,"slug":"analyzing-large-receptive-field-convolutional","title":"Analyzing Large Receptive Field Convolutional Networks for Distant Speech Recognition","date":"2019-10-15","arxiv_id":"1910.07047","n_code_links":0,"syntology":null},{"paper":"/paper/enhancing-the-transformer-with-explicit-1","slug":"enhancing-the-transformer-with-explicit-1","title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","date":"2019-10-15","arxiv_id":"1910.06611","n_code_links":3,"syntology":{"ran":8,"of":11,"n_ran_checked":8,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["ischlag/TP-Transformer"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"facebook-ais-wat19-myanmar-english","title":"Facebook AI's WAT19 Myanmar-English Translation Task Submission","date":"2019-10-15","arxiv_id":"1910.06848","n_code_links":0,"syntology":null},{"paper":null,"slug":"full-scale-continuous-synthetic-sonar-data","title":"Full-Scale Continuous Synthetic Sonar Data Generation with Markov Conditional Generative Adversarial Networks","date":"2019-10-15","arxiv_id":"1910.06750","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-tangent-kernels-transportation-1","title":"Neural tangent kernels, transportation mappings, and universal approximation","date":"2019-10-15","arxiv_id":"1910.06956","n_code_links":0,"syntology":null},{"paper":null,"slug":"icps-net-an-end-to-end-rgb-based-indoor","title":"ICPS-net: An End-to-End RGB-based Indoor Camera Positioning System using deep convolutional neural networks","date":"2019-10-14","arxiv_id":"1910.06219","n_code_links":0,"syntology":null},{"paper":"/paper/learning-sparsity-and-quantization-jointly","slug":"learning-sparsity-and-quantization-jointly","title":"Automatic Neural Network Compression by Sparsity-Quantization Joint Learning: A Constrained Optimization-based Approach","date":"2019-10-14","arxiv_id":"1910.05897","n_code_links":1,"syntology":null},{"paper":null,"slug":"pruning-a-bert-based-question-answering-model","title":"Structured Pruning of a BERT-based Question Answering Model","date":"2019-10-14","arxiv_id":"1910.06360","n_code_links":0,"syntology":null},{"paper":"/paper/q8bert-quantized-8bit-bert","slug":"q8bert-quantized-8bit-bert","title":"Q8BERT: Quantized 8Bit BERT","date":"2019-10-14","arxiv_id":"1910.06188","n_code_links":5,"syntology":{"ran":10,"of":11,"n_ran_checked":9,"n_instrument":1,"unverified":1,"pointer_only":3,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["intellabs/model-compression-research-package","NervanaSystems/nlp-architect"],"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":["listed","official","unlocated"]}}},{"paper":"/paper/robust-compressive-sensing-mri-reconstruction","slug":"robust-compressive-sensing-mri-reconstruction","title":"Structure Preserving Compressive Sensing MRI Reconstruction using Generative Adversarial Networks","date":"2019-10-14","arxiv_id":"1910.06067","n_code_links":1,"syntology":null},{"paper":"/paper/transformers-without-tears-improving-the","slug":"transformers-without-tears-improving-the","title":"Transformers without Tears: Improving the Normalization of Self-Attention","date":"2019-10-14","arxiv_id":"1910.05895","n_code_links":5,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["tnq177/transformers_without_tears"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/vertebrae-detection-and-localization-in-ct","slug":"vertebrae-detection-and-localization-in-ct","title":"Vertebrae Detection and Localization in CT with Two-Stage CNNs and Dense Annotations","date":"2019-10-14","arxiv_id":"1910.05911","n_code_links":1,"syntology":null},{"paper":null,"slug":"generalization-bounds-for-neural-networks-via","title":"Generalization Bounds for Neural Networks via Approximate Description Length","date":"2019-10-13","arxiv_id":"1910.05697","n_code_links":0,"syntology":null},{"paper":null,"slug":"if-dropout-limits-trainable-depth-does","title":"If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks","date":"2019-10-13","arxiv_id":"1910.05725","n_code_links":0,"syntology":null},{"paper":null,"slug":"large-deviation-analysis-of-function","title":"Large Deviation Analysis of Function Sensitivity in Random Deep Neural Networks","date":"2019-10-13","arxiv_id":"1910.05769","n_code_links":0,"syntology":null},{"paper":null,"slug":"radiomic-feature-stability-analysis-based-on","title":"Radiomic Feature Stability Analysis based on Probabilistic Segmentations","date":"2019-10-13","arxiv_id":"1910.05693","n_code_links":0,"syntology":null},{"paper":"/paper/stabilizing-transformers-for-reinforcement-1","slug":"stabilizing-transformers-for-reinforcement-1","title":"Stabilizing Transformers for Reinforcement Learning","date":"2019-10-13","arxiv_id":"1910.06764","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: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"how-are-attributes-expressed-in-face-dcnns","title":"How are attributes expressed in face DCNNs?","date":"2019-10-12","arxiv_id":"1910.05657","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-expected-behaviour-of-noise","title":"On the expected behaviour of noise regularised deep neural networks as Gaussian processes","date":"2019-10-12","arxiv_id":"1910.05563","n_code_links":0,"syntology":null},{"paper":"/paper/aff-wild-database-and-affwildnet","slug":"aff-wild-database-and-affwildnet","title":"Aff-Wild Database and AffWildNet","date":"2019-10-11","arxiv_id":"1910.05318","n_code_links":1,"syntology":null},{"paper":"/paper/deep-independently-recurrent-neural-network","slug":"deep-independently-recurrent-neural-network","title":"Deep Independently Recurrent Neural Network (IndRNN)","date":"2019-10-11","arxiv_id":"1910.06251","n_code_links":1,"syntology":null},{"paper":null,"slug":"illegible-text-to-readable-text-an-image-to","title":"Illegible Text to Readable Text: An Image-to-Image Transformation using Conditional Sliced Wasserstein Adversarial Networks","date":"2019-10-11","arxiv_id":"1910.05425","n_code_links":0,"syntology":null},{"paper":null,"slug":"shape-constrained-network-for-eye","title":"Shape Constrained Network for Eye Segmentation in the Wild","date":"2019-10-11","arxiv_id":"1910.05283","n_code_links":0,"syntology":null},{"paper":"/paper/improving-sample-diversity-of-a-pre-trained","slug":"improving-sample-diversity-of-a-pre-trained","title":"A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings","date":"2019-10-10","arxiv_id":"1910.04760","n_code_links":1,"syntology":null},{"paper":"/paper/on-recognizing-texts-of-arbitrary-shapes-with","slug":"on-recognizing-texts-of-arbitrary-shapes-with","title":"On Recognizing Texts of Arbitrary Shapes with 2D Self-Attention","date":"2019-10-10","arxiv_id":"1910.04396","n_code_links":2,"syntology":null},{"paper":"/paper/3d-manhattan-room-layout-reconstruction-from","slug":"3d-manhattan-room-layout-reconstruction-from","title":"Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methods","date":"2019-10-09","arxiv_id":"1910.04099","n_code_links":3,"syntology":null},{"paper":null,"slug":"ctrl-z-recovering-from-instability-in","title":"Ctrl-Z: Recovering from Instability in Reinforcement Learning","date":"2019-10-09","arxiv_id":"1910.03732","n_code_links":0,"syntology":null},{"paper":"/paper/on-the-adequacy-of-untuned-warmup-for","slug":"on-the-adequacy-of-untuned-warmup-for","title":"On the adequacy of untuned warmup for adaptive optimization","date":"2019-10-09","arxiv_id":"1910.04209","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"pointer_only":0,"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) · 0 unverified","official":null}},{"paper":"/paper/pipemare-asynchronous-pipeline-parallel-dnn","slug":"pipemare-asynchronous-pipeline-parallel-dnn","title":"PipeMare: Asynchronous Pipeline Parallel DNN Training","date":"2019-10-09","arxiv_id":"1910.05124","n_code_links":0,"syntology":null},{"paper":"/paper/prescribed-generative-adversarial-networks","slug":"prescribed-generative-adversarial-networks","title":"Prescribed Generative Adversarial Networks","date":"2019-10-09","arxiv_id":"1910.04302","n_code_links":2,"syntology":null},{"paper":"/paper/transformers-state-of-the-art-natural","slug":"transformers-state-of-the-art-natural","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","date":"2019-10-09","arxiv_id":"1910.03771","n_code_links":9,"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":["huggingface/transformers"],"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/deep-network-classification-by-scattering-and","slug":"deep-network-classification-by-scattering-and","title":"Deep Network Classification by Scattering and Homotopy Dictionary Learning","date":"2019-10-08","arxiv_id":"1910.03561","n_code_links":1,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":0,"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) · 2 unverified","official":{"repos":["j-zarka/SparseScatNet"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/eca-net-efficient-channel-attention-for-deep","slug":"eca-net-efficient-channel-attention-for-deep","title":"ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks","date":"2019-10-08","arxiv_id":"1910.03151","n_code_links":13,"syntology":{"ran":3,"of":8,"n_ran_checked":2,"n_instrument":1,"unverified":5,"pointer_only":1,"phrase":"3 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; 1 where Syntology's instrument failed) · 5 unverified","official":{"repos":["BangguWu/ECANet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"inferring-dynamical-systems-with-long-range","title":"Identifying nonlinear dynamical systems with multiple time scales and long-range dependencies","date":"2019-10-08","arxiv_id":"1910.03471","n_code_links":0,"syntology":null},{"paper":"/paper/multi-source-domain-adaptation-and-semi","slug":"multi-source-domain-adaptation-and-semi","title":"Multi-Source Domain Adaptation and Semi-Supervised Domain Adaptation with Focus on Visual Domain Adaptation Challenge 2019","date":"2019-10-08","arxiv_id":"1910.03548","n_code_links":2,"syntology":null},{"paper":null,"slug":"person-re-identification-based-on-res2net","title":"Improved Res2Net model for Person re-identification","date":"2019-10-08","arxiv_id":"1910.04061","n_code_links":0,"syntology":null},{"paper":"/paper/torchbeast-a-pytorch-platform-for-distributed","slug":"torchbeast-a-pytorch-platform-for-distributed","title":"TorchBeast: A PyTorch Platform for Distributed RL","date":"2019-10-08","arxiv_id":"1910.03552","n_code_links":3,"syntology":{"ran":6,"of":9,"n_ran_checked":2,"n_instrument":4,"unverified":3,"pointer_only":3,"phrase":"6 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; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["heiner/scalable_agent"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official","unlocated"]}}},{"paper":null,"slug":"universal-approximation-theorems","title":"The Universal Approximation Property","date":"2019-10-08","arxiv_id":"1910.03344","n_code_links":0,"syntology":null},{"paper":"/paper/deformable-kernels-adapting-effective","slug":"deformable-kernels-adapting-effective","title":"Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation","date":"2019-10-07","arxiv_id":"1910.02940","n_code_links":2,"syntology":null},{"paper":null,"slug":"neural-network-integral-representations-with","title":"Neural network integral representations with the ReLU activation function","date":"2019-10-07","arxiv_id":"1910.02743","n_code_links":0,"syntology":null},{"paper":"/paper/noise-as-domain-shift-denoising-medical","slug":"noise-as-domain-shift-denoising-medical","title":"Noise as Domain Shift: Denoising Medical Images by Unpaired Image Translation","date":"2019-10-07","arxiv_id":"1910.02702","n_code_links":1,"syntology":null}],"record_sha256":"b8d751d90de3a48d28dcfc2006285afa9b7a4d86c3e70d23d8fee9b2daded8c7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}