{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/softmax/papers/345","list_of":"/method/softmax","method":"Softmax","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":345,"pages_in_order":375,"rows_per_page":100,"rows":[34401,34500],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/method/softmax","prev":"/method/softmax/papers/344","next":"/method/softmax/papers/346","papers":[{"paper":"/paper/voice-transformer-network-sequence-to","slug":"voice-transformer-network-sequence-to","title":"Voice Transformer Network: Sequence-to-Sequence Voice Conversion Using Transformer with Text-to-Speech Pretraining","date":"2019-12-14","arxiv_id":"1912.06813","n_code_links":2,"syntology":null},{"paper":"/paper/action-modifiers-learning-from-adverbs-in","slug":"action-modifiers-learning-from-adverbs-in","title":"Action Modifiers: Learning from Adverbs in Instructional Videos","date":"2019-12-13","arxiv_id":"1912.06617","n_code_links":1,"syntology":null},{"paper":"/paper/liteseg-a-novel-lightweight-convnet-for","slug":"liteseg-a-novel-lightweight-convnet-for","title":"LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation","date":"2019-12-13","arxiv_id":"1912.06683","n_code_links":2,"syntology":null},{"paper":"/paper/pain-evaluation-in-video-using-extended","slug":"pain-evaluation-in-video-using-extended","title":"Pain Evaluation in Video using Extended Multitask Learning from Multidimensional Measurements","date":"2019-12-13","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/previous-a-methodology-for-prediction-of","slug":"previous-a-methodology-for-prediction-of","title":"PreVIous: A Methodology for Prediction of Visual Inference Performance on IoT Devices","date":"2019-12-13","arxiv_id":"1912.06442","n_code_links":1,"syntology":null},{"paper":"/paper/topoact-exploring-the-shape-of-activations-in","slug":"topoact-exploring-the-shape-of-activations-in","title":"TopoAct: Visually Exploring the Shape of Activations in Deep Learning","date":"2019-12-13","arxiv_id":"1912.06332","n_code_links":1,"syntology":null},{"paper":null,"slug":"waldorf-wasteless-language-model-distillation","title":"WaLDORf: Wasteless Language-model Distillation On Reading-comprehension","date":"2019-12-13","arxiv_id":"1912.06638","n_code_links":0,"syntology":null},{"paper":null,"slug":"grid-search-random-search-genetic-algorithm-a","title":"Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS","date":"2019-12-12","arxiv_id":"1912.06059","n_code_links":0,"syntology":null},{"paper":"/paper/the-benefits-of-close-domain-fine-tuning-for","slug":"the-benefits-of-close-domain-fine-tuning-for","title":"The Benefits of Close-Domain Fine-Tuning for Table Detection in Document Images","date":"2019-12-12","arxiv_id":"1912.05846","n_code_links":1,"syntology":null},{"paper":"/paper/a-variational-sequential-graph-autoencoder","slug":"a-variational-sequential-graph-autoencoder","title":"A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction","date":"2019-12-11","arxiv_id":"1912.05317","n_code_links":1,"syntology":null},{"paper":"/paper/augfpn-improving-multi-scale-feature-learning","slug":"augfpn-improving-multi-scale-feature-learning","title":"AugFPN: Improving Multi-scale Feature Learning for Object Detection","date":"2019-12-11","arxiv_id":"1912.05384","n_code_links":2,"syntology":null},{"paper":null,"slug":"bert-has-a-moral-compass-improvements-of","title":"BERT has a Moral Compass: Improvements of ethical and moral values of machines","date":"2019-12-11","arxiv_id":"1912.05238","n_code_links":0,"syntology":null},{"paper":null,"slug":"fine-grained-classification-of-rowing-teams","title":"Fine-grained Classification of Rowing teams","date":"2019-12-11","arxiv_id":"1912.05393","n_code_links":0,"syntology":null},{"paper":"/paper/histonet-predicting-size-histograms-of-object","slug":"histonet-predicting-size-histograms-of-object","title":"HistoNet: Predicting size histograms of object instances","date":"2019-12-11","arxiv_id":"1912.05227","n_code_links":1,"syntology":null},{"paper":"/paper/linear-mode-connectivity-and-the-lottery","slug":"linear-mode-connectivity-and-the-lottery","title":"Linear Mode Connectivity and the Lottery Ticket Hypothesis","date":"2019-12-11","arxiv_id":"1912.05671","n_code_links":2,"syntology":null},{"paper":"/paper/robust-gabor-networks","slug":"robust-gabor-networks","title":"Gabor Layers Enhance Network Robustness","date":"2019-12-11","arxiv_id":"1912.05661","n_code_links":1,"syntology":null},{"paper":"/paper/unet-redesigning-skip-connections-to-exploit","slug":"unet-redesigning-skip-connections-to-exploit","title":"UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation","date":"2019-12-11","arxiv_id":"1912.05074","n_code_links":13,"syntology":{"ran":4,"of":9,"n_ran_checked":3,"n_instrument":1,"unverified":5,"pointer_only":3,"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) · 5 unverified","official":{"repos":["MrGiovanni/UNetPlusPlus"],"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":"classifying-segmenting-and-tracking-object","title":"Classifying, Segmenting, and Tracking Object Instances in Video with Mask Propagation","date":"2019-12-10","arxiv_id":"1912.04573","n_code_links":0,"syntology":null},{"paper":"/paper/diffeomorphic-temporal-alignment-nets","slug":"diffeomorphic-temporal-alignment-nets","title":"Diffeomorphic Temporal Alignment Nets","date":"2019-12-10","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"encoding-musical-style-with-transformer-1","title":"Encoding Musical Style with Transformer Autoencoders","date":"2019-12-10","arxiv_id":"1912.05537","n_code_links":0,"syntology":null},{"paper":"/paper/removable-andor-repeated-units-emerge-in","slug":"removable-andor-repeated-units-emerge-in","title":"Frivolous Units: Wider Networks Are Not Really That Wide","date":"2019-12-10","arxiv_id":"1912.04783","n_code_links":1,"syntology":null},{"paper":"/paper/solo-segmenting-objects-by-locations","slug":"solo-segmenting-objects-by-locations","title":"SOLO: Segmenting Objects by Locations","date":"2019-12-10","arxiv_id":"1912.04488","n_code_links":24,"syntology":null},{"paper":"/paper/spinenet-learning-scale-permuted-backbone-for","slug":"spinenet-learning-scale-permuted-backbone-for","title":"SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization","date":"2019-12-10","arxiv_id":"1912.05027","n_code_links":13,"syntology":null},{"paper":null,"slug":"unsupervised-transfer-learning-via-bert","title":"Unsupervised Transfer Learning via BERT Neuron Selection","date":"2019-12-10","arxiv_id":"1912.05308","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-empirical-study-on-position-of-the-batch","title":"An Empirical Study on Position of the Batch Normalization Layer in Convolutional Neural Networks","date":"2019-12-09","arxiv_id":"1912.04259","n_code_links":0,"syntology":null},{"paper":null,"slug":"intelligent-coordination-among-multiple","title":"Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning","date":"2019-12-09","arxiv_id":"1912.03851","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-a-layout-transfer-network-for","title":"Learning a Layout Transfer Network for Context Aware Object Detection","date":"2019-12-09","arxiv_id":"1912.03865","n_code_links":0,"syntology":null},{"paper":"/paper/side-aware-boundary-localization-for-more","slug":"side-aware-boundary-localization-for-more","title":"Side-Aware Boundary Localization for More Precise Object Detection","date":"2019-12-09","arxiv_id":"1912.04260","n_code_links":3,"syntology":null},{"paper":null,"slug":"stealing-knowledge-from-protected-deep-neural","title":"Stealing Knowledge from Protected Deep Neural Networks Using Composite Unlabeled Data","date":"2019-12-09","arxiv_id":"1912.03959","n_code_links":0,"syntology":null},{"paper":null,"slug":"transformer-based-reinforcement-learning-for","title":"Transformer Based Reinforcement Learning For Games","date":"2019-12-09","arxiv_id":"1912.03918","n_code_links":0,"syntology":null},{"paper":"/paper/bidirectional-scene-text-recognition-with-a","slug":"bidirectional-scene-text-recognition-with-a","title":"Bidirectional Scene Text Recognition with a Single Decoder","date":"2019-12-08","arxiv_id":"1912.03656","n_code_links":1,"syntology":null},{"paper":"/paper/individual-predictions-matter-assessing-the","slug":"individual-predictions-matter-assessing-the","title":"Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging","date":"2019-12-08","arxiv_id":"1912.03606","n_code_links":1,"syntology":null},{"paper":"/paper/salite-a-light-weight-model-for-salient","slug":"salite-a-light-weight-model-for-salient","title":"SaLite : A light-weight model for salient object detection","date":"2019-12-08","arxiv_id":"1912.03641","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-analysis-of-natural-language","title":"Adversarial Analysis of Natural Language Inference Systems","date":"2019-12-07","arxiv_id":"1912.03441","n_code_links":0,"syntology":null},{"paper":null,"slug":"personalized-patent-claim-generation-and","title":"Personalized Patent Claim Generation and Measurement","date":"2019-12-07","arxiv_id":"1912.03502","n_code_links":0,"syntology":null},{"paper":null,"slug":"alternative-function-approximation","title":"Alternative Function Approximation Parameterizations for Solving Games: An Analysis of $f$-Regression Counterfactual Regret Minimization","date":"2019-12-06","arxiv_id":"1912.02967","n_code_links":0,"syntology":null},{"paper":"/paper/semantic-mask-for-transformer-based-end-to","slug":"semantic-mask-for-transformer-based-end-to","title":"Semantic Mask for Transformer based End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.03010","n_code_links":1,"syntology":null},{"paper":null,"slug":"synchronous-transformers-for-end-to-end","title":"Synchronous Transformers for End-to-End Speech Recognition","date":"2019-12-06","arxiv_id":"1912.02958","n_code_links":0,"syntology":null},{"paper":null,"slug":"weak-supervision-helps-emergence-of-word","title":"Weak Supervision helps Emergence of Word-Object Alignment and improves Vision-Language Tasks","date":"2019-12-06","arxiv_id":"1912.03063","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-adam-beats-sgd-for-attention-models-1","title":"Why are Adaptive Methods Good for Attention Models?","date":"2019-12-06","arxiv_id":"1912.03194","n_code_links":0,"syntology":null},{"paper":null,"slug":"phonebit-efficient-gpu-accelerated-binary","title":"PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones","date":"2019-12-05","arxiv_id":"1912.04050","n_code_links":0,"syntology":null},{"paper":"/paper/scratch-that-an-evolution-based-adversarial","slug":"scratch-that-an-evolution-based-adversarial","title":"Scratch that! An Evolution-based Adversarial Attack against Neural Networks","date":"2019-12-05","arxiv_id":"1912.02316","n_code_links":1,"syntology":null},{"paper":null,"slug":"self-supervised-contextual-language","title":"Self-Supervised Contextual Language Representation of Radiology Reports to Improve the Identification of Communication Urgency","date":"2019-12-05","arxiv_id":"1912.02703","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-robust-neural-vocoding-for-speech","title":"Towards Robust Neural Vocoding for Speech Generation: A Survey","date":"2019-12-05","arxiv_id":"1912.02461","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultrafast-photorealistic-style-transfer-via","title":"Ultrafast Photorealistic Style Transfer via Neural Architecture Search","date":"2019-12-05","arxiv_id":"1912.02398","n_code_links":0,"syntology":null},{"paper":null,"slug":"acquiring-knowledge-from-pre-trained-model-to","title":"Acquiring Knowledge from Pre-trained Model to Neural Machine Translation","date":"2019-12-04","arxiv_id":"1912.01774","n_code_links":0,"syntology":null},{"paper":null,"slug":"amused-a-multi-stream-vector-representation-1","title":"AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue","date":"2019-12-04","arxiv_id":"1912.10160","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-exploration-of-data-augmentation-and-1","title":"An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering","date":"2019-12-04","arxiv_id":"1912.02145","n_code_links":0,"syntology":null},{"paper":"/paper/embedmask-embedding-coupling-for-one-stage","slug":"embedmask-embedding-coupling-for-one-stage","title":"EmbedMask: Embedding Coupling for One-stage Instance Segmentation","date":"2019-12-04","arxiv_id":"1912.01954","n_code_links":3,"syntology":null},{"paper":"/paper/enhancing-relation-extraction-using-syntactic","slug":"enhancing-relation-extraction-using-syntactic","title":"Enhancing Relation Extraction Using Syntactic Indicators and Sentential Contexts","date":"2019-12-04","arxiv_id":"1912.01858","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-comparative-study-of-pretrained-language","title":"A Comparative Study of Pretrained Language Models on Thai Social Text Categorization","date":"2019-12-03","arxiv_id":"1912.01580","n_code_links":0,"syntology":null},{"paper":null,"slug":"edas-efficient-and-differentiable","title":"EDAS: Efficient and Differentiable Architecture Search","date":"2019-12-03","arxiv_id":"1912.01237","n_code_links":0,"syntology":null},{"paper":"/paper/multi-criterion-evolutionary-design-of-deep","slug":"multi-criterion-evolutionary-design-of-deep","title":"Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification","date":"2019-12-03","arxiv_id":"1912.01369","n_code_links":1,"syntology":null},{"paper":"/paper/tu-wien-trec-deep-learning-19-simple","slug":"tu-wien-trec-deep-learning-19-simple","title":"TU Wien @ TREC Deep Learning '19 -- Simple Contextualization for Re-ranking","date":"2019-12-03","arxiv_id":"1912.01385","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-robust-iris-authentication-system-on-gpu","title":"Learning scale-variant features for robust iris authentication with deep learning based ensemble framework","date":"2019-12-02","arxiv_id":"1912.00756","n_code_links":0,"syntology":null},{"paper":null,"slug":"audiovisual-transformer-architectures-for","title":"Audiovisual Transformer Architectures for Large-Scale Classification and Synchronization of Weakly Labeled Audio Events","date":"2019-12-02","arxiv_id":"1912.02615","n_code_links":0,"syntology":null},{"paper":null,"slug":"bert-for-large-scale-video-segment","title":"BERT for Large-scale Video Segment Classification with Test-time Augmentation","date":"2019-12-02","arxiv_id":"1912.01127","n_code_links":0,"syntology":null},{"paper":"/paper/blimp-a-benchmark-of-linguistic-minimal-pairs","slug":"blimp-a-benchmark-of-linguistic-minimal-pairs","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","date":"2019-12-02","arxiv_id":"1912.00582","n_code_links":4,"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":{"repos":["alexwarstadt/blimp","alexwarstadt/data_generation"],"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":"detecting-gan-generated-errors","title":"Detecting GAN generated errors","date":"2019-12-02","arxiv_id":"1912.00527","n_code_links":0,"syntology":null},{"paper":"/paper/ft-clipact-resilience-analysis-of-deep-neural","slug":"ft-clipact-resilience-analysis-of-deep-neural","title":"FT-ClipAct: Resilience Analysis of Deep Neural Networks and Improving their Fault Tolerance using Clipped Activation","date":"2019-12-02","arxiv_id":"1912.00941","n_code_links":1,"syntology":null},{"paper":null,"slug":"leveraging-contextual-embeddings-for","title":"Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift","date":"2019-12-02","arxiv_id":"1912.01072","n_code_links":0,"syntology":null},{"paper":"/paper/logan-latent-optimisation-for-generative-1","slug":"logan-latent-optimisation-for-generative-1","title":"LOGAN: Latent Optimisation for Generative Adversarial Networks","date":"2019-12-02","arxiv_id":"1912.00953","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":4,"n_instrument":1,"unverified":3,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":"/paper/long-distance-relationships-without-time","slug":"long-distance-relationships-without-time","title":"Long Distance Relationships without Time Travel: Boosting the Performance of a Sparse Predictive Autoencoder in Sequence Modeling","date":"2019-12-02","arxiv_id":"1912.01116","n_code_links":1,"syntology":null},{"paper":"/paper/mnasfpn-learning-latency-aware-pyramid","slug":"mnasfpn-learning-latency-aware-pyramid","title":"MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices","date":"2019-12-02","arxiv_id":"1912.01106","n_code_links":2,"syntology":null},{"paper":null,"slug":"multi-scale-self-attention-for-text","title":"Multi-Scale Self-Attention for Text Classification","date":"2019-12-02","arxiv_id":"1912.00544","n_code_links":0,"syntology":null},{"paper":"/paper/neural-academic-paper-generation","slug":"neural-academic-paper-generation","title":"Neural Academic Paper Generation","date":"2019-12-02","arxiv_id":"1912.01982","n_code_links":1,"syntology":null},{"paper":null,"slug":"red-cane-a-systematic-methodology-for","title":"ReD-CaNe: A Systematic Methodology for Resilience Analysis and Design of Capsule Networks under Approximations","date":"2019-12-02","arxiv_id":"1912.00700","n_code_links":0,"syntology":null},{"paper":"/paper/solving-arithmetic-word-problems","slug":"solving-arithmetic-word-problems","title":"Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations","date":"2019-12-02","arxiv_id":"1912.00871","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversary-a3c-for-robust-reinforcement-1","title":"Adversary A3C for Robust Reinforcement Learning","date":"2019-12-01","arxiv_id":"1912.00330","n_code_links":0,"syntology":null},{"paper":"/paper/autoprune-automatic-network-pruning-by","slug":"autoprune-automatic-network-pruning-by","title":"AutoPrune: Automatic Network Pruning by Regularizing Auxiliary Parameters","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/beyond-temperature-scaling-obtaining-well-1","slug":"beyond-temperature-scaling-obtaining-well-1","title":"Beyond temperature scaling: Obtaining well-calibrated multi-class probabilities with Dirichlet calibration","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"efficient-neural-architecture-transformation-1","title":"Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/fast-and-accurate-stochastic-gradient","slug":"fast-and-accurate-stochastic-gradient","title":"Fast and Accurate Stochastic Gradient Estimation","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"hybrid-8-bit-floating-point-hfp8-training-and","title":"Hybrid 8-bit Floating Point (HFP8) Training and Inference for Deep Neural Networks","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-reward-machines-for-partially","slug":"learning-reward-machines-for-partially","title":"Learning Reward Machines for Partially Observable Reinforcement Learning","date":"2019-12-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"maximum-entropy-monte-carlo-planning","title":"Maximum Entropy Monte-Carlo Planning","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"metadapt-meta-learned-task-adaptive","title":"MetAdapt: Meta-Learned Task-Adaptive Architecture for Few-Shot Classification","date":"2019-12-01","arxiv_id":"1912.00412","n_code_links":0,"syntology":null},{"paper":null,"slug":"mixtape-breaking-the-softmax-bottleneck","title":"Mixtape: Breaking the Softmax Bottleneck Efficiently","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"multilabel-reductions-what-is-my-loss","title":"Multilabel reductions: what is my loss optimising?","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"perceiving-the-arrow-of-time-in","title":"Perceiving the arrow of time in autoregressive motion","date":"2019-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"pruning-at-a-glance-global-neural-pruning-for","title":"Pruning at a Glance: Global Neural Pruning for Model Compression","date":"2019-11-30","arxiv_id":"1912.00200","n_code_links":0,"syntology":null},{"paper":"/paper/sgas-sequential-greedy-architecture-search","slug":"sgas-sequential-greedy-architecture-search","title":"SGAS: Sequential Greedy Architecture Search","date":"2019-11-30","arxiv_id":"1912.00195","n_code_links":1,"syntology":{"ran":3,"of":7,"n_ran_checked":3,"n_instrument":0,"unverified":4,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":null}},{"paper":null,"slug":"towards-oracle-knowledge-distillation-with","title":"Towards Oracle Knowledge Distillation with Neural Architecture Search","date":"2019-11-29","arxiv_id":"1911.13019","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-driven-compression-of-convolutional","title":"Data-Driven Compression of Convolutional Neural Networks","date":"2019-11-28","arxiv_id":"1911.12740","n_code_links":0,"syntology":null},{"paper":null,"slug":"inducing-relational-knowledge-from-bert","title":"Inducing Relational Knowledge from BERT","date":"2019-11-28","arxiv_id":"1911.12753","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimum-bayes-risk-training-of-rnn-transducer","title":"Minimum Bayes Risk Training of RNN-Transducer for End-to-End Speech Recognition","date":"2019-11-28","arxiv_id":"1911.12487","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-generation-of-headlines-for-online","slug":"automatic-generation-of-headlines-for-online","title":"Automatic Generation of Headlines for Online Math Questions","date":"2019-11-27","arxiv_id":"1912.00839","n_code_links":1,"syntology":null},{"paper":"/paper/crypto-oriented-neural-architecture-design","slug":"crypto-oriented-neural-architecture-design","title":"Crypto-Oriented Neural Architecture Design","date":"2019-11-27","arxiv_id":"1911.12322","n_code_links":1,"syntology":null},{"paper":"/paper/cspnet-a-new-backbone-that-can-enhance","slug":"cspnet-a-new-backbone-that-can-enhance","title":"CSPNet: A New Backbone that can Enhance Learning Capability of CNN","date":"2019-11-27","arxiv_id":"1911.11929","n_code_links":123,"syntology":null},{"paper":"/paper/define-deep-factorized-input-word-embeddings-1","slug":"define-deep-factorized-input-word-embeddings-1","title":"DeFINE: DEep Factorized INput Token Embeddings for Neural Sequence Modeling","date":"2019-11-27","arxiv_id":"1911.12385","n_code_links":1,"syntology":null},{"paper":"/paper/do-attention-heads-in-bert-track-syntactic","slug":"do-attention-heads-in-bert-track-syntactic","title":"Do Attention Heads in BERT Track Syntactic Dependencies?","date":"2019-11-27","arxiv_id":"1911.12246","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-commonsense-in-pre-trained","slug":"evaluating-commonsense-in-pre-trained","title":"Evaluating Commonsense in Pre-trained Language Models","date":"2019-11-27","arxiv_id":"1911.11931","n_code_links":1,"syntology":null},{"paper":"/paper/fair-darts-eliminating-unfair-advantages-in","slug":"fair-darts-eliminating-unfair-advantages-in","title":"Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search","date":"2019-11-27","arxiv_id":"1911.12126","n_code_links":1,"syntology":null},{"paper":"/paper/ghostnet-more-features-from-cheap-operations","slug":"ghostnet-more-features-from-cheap-operations","title":"GhostNet: More Features from Cheap Operations","date":"2019-11-27","arxiv_id":"1911.11907","n_code_links":33,"syntology":{"ran":19,"of":23,"n_ran_checked":16,"n_instrument":3,"unverified":4,"pointer_only":5,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified","official":{"repos":["huawei-noah/ghostnet"],"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":"simplebooks-long-term-dependency-book-dataset","title":"SimpleBooks: Long-term dependency book dataset with simplified English vocabulary for word-level language modeling","date":"2019-11-27","arxiv_id":"1911.12391","n_code_links":0,"syntology":null},{"paper":null,"slug":"taking-a-stance-on-fake-news-towards","title":"Taking a Stance on Fake News: Towards Automatic Disinformation Assessment via Deep Bidirectional Transformer Language Models for Stance Detection","date":"2019-11-27","arxiv_id":"1911.11951","n_code_links":0,"syntology":null},{"paper":"/paper/your-local-gan-designing-two-dimensional","slug":"your-local-gan-designing-two-dimensional","title":"Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models","date":"2019-11-27","arxiv_id":"1911.12287","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["giannisdaras/ylg"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/autoencoding-undirected-molecular-graphs-with","slug":"autoencoding-undirected-molecular-graphs-with","title":"Autoencoding Undirected Molecular Graphs With Neural Networks","date":"2019-11-26","arxiv_id":"2001.03517","n_code_links":1,"syntology":null},{"paper":"/paper/efficient-attention-mechanism-for-handling","slug":"efficient-attention-mechanism-for-handling","title":"Efficient Attention Mechanism for Visual Dialog that can Handle All the Interactions between Multiple Inputs","date":"2019-11-26","arxiv_id":"1911.11390","n_code_links":1,"syntology":null},{"paper":"/paper/improving-polyphonic-music-models-with","slug":"improving-polyphonic-music-models-with","title":"Improving Polyphonic Music Models with Feature-Rich Encoding","date":"2019-11-26","arxiv_id":"1911.11775","n_code_links":2,"syntology":null}],"record_sha256":"24ea7a74febc06990d654bbd3b180bdc38eabc432ff0882ac2a7aa7b01c51d37","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}