{"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/knowledge-distillation/papers/31","list_of":"/method/knowledge-distillation","method":"Knowledge Distillation","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":31,"pages_in_order":31,"rows_per_page":100,"rows":[3001,3071],"of":3071,"counts":{"archive_papers_tagged":3071,"with_a_code_link":1258,"where_syntology_ran_a_sample":320,"not_listed_spam_title":0,"listed":3071,"listed_where_code_ran":320,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":276,"every_run_a_failure_of_syntologys_instrument":44,"listed_with_a_run_with_no_instrument_failure":276,"listed_every_run_a_failure_of_syntologys_instrument":44,"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/knowledge-distillation","prev":"/method/knowledge-distillation/papers/30","next":null,"papers":[{"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":"segmenting-the-future","title":"Segmenting the Future","date":"2019-04-24","arxiv_id":"1904.10666","n_code_links":0,"syntology":null},{"paper":"/paper/190501976","slug":"190501976","title":"TextKD-GAN: Text Generation using KnowledgeDistillation and Generative Adversarial Networks","date":"2019-04-23","arxiv_id":"1905.01976","n_code_links":1,"syntology":null},{"paper":null,"slug":"model-compression-with-multi-task-knowledge","title":"Model Compression with Multi-Task Knowledge Distillation for Web-scale Question Answering System","date":"2019-04-21","arxiv_id":"1904.09636","n_code_links":0,"syntology":null},{"paper":"/paper/improving-multi-task-deep-neural-networks-via","slug":"improving-multi-task-deep-neural-networks-via","title":"Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding","date":"2019-04-20","arxiv_id":"1904.09482","n_code_links":3,"syntology":null},{"paper":"/paper/knowledge-distillation-via-route-constrained","slug":"knowledge-distillation-via-route-constrained","title":"Knowledge Distillation via Route Constrained Optimization","date":"2019-04-19","arxiv_id":"1904.09149","n_code_links":1,"syntology":null},{"paper":null,"slug":"end-to-end-speech-translation-with-knowledge","title":"End-to-End Speech Translation with Knowledge Distillation","date":"2019-04-17","arxiv_id":"1904.08075","n_code_links":0,"syntology":null},{"paper":null,"slug":"guiding-ctc-posterior-spike-timings-for","title":"Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillation","date":"2019-04-17","arxiv_id":"1904.08311","n_code_links":0,"syntology":null},{"paper":"/paper/visual-relationship-detection-with-language-1","slug":"visual-relationship-detection-with-language-1","title":"Visual Relationship Detection with Language prior and Softmax","date":"2019-04-16","arxiv_id":"1904.07798","n_code_links":1,"syntology":null},{"paper":"/paper/automatic-adaptation-of-object-detectors-to","slug":"automatic-adaptation-of-object-detectors-to","title":"Automatic adaptation of object detectors to new domains using self-training","date":"2019-04-15","arxiv_id":"1904.07305","n_code_links":1,"syntology":{"ran":8,"of":18,"n_ran_checked":8,"n_instrument":0,"unverified":10,"pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified","official":null}},{"paper":"/paper/improved-training-of-binary-networks-for","slug":"improved-training-of-binary-networks-for","title":"Improved training of binary networks for human pose estimation and image recognition","date":"2019-04-11","arxiv_id":"1904.05868","n_code_links":1,"syntology":null},{"paper":"/paper/relational-knowledge-distillation","slug":"relational-knowledge-distillation","title":"Relational Knowledge Distillation","date":"2019-04-10","arxiv_id":"1904.05068","n_code_links":3,"syntology":{"ran":2,"of":3,"n_ran_checked":1,"n_instrument":1,"unverified":1,"pointer_only":1,"phrase":"2 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; 1 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"back-to-the-future-knowledge-distillation-for","title":"Knowledge Distillation for Human Action Anticipation","date":"2019-04-09","arxiv_id":"1904.04868","n_code_links":0,"syntology":null},{"paper":null,"slug":"ultrafast-video-attention-prediction-with","title":"Ultrafast Video Attention Prediction with Coupled Knowledge Distillation","date":"2019-04-09","arxiv_id":"1904.04449","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-recurrent-neural","title":"Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization","date":"2019-04-08","arxiv_id":"1904.04163","n_code_links":0,"syntology":null},{"paper":"/paper/correlation-congruence-for-knowledge","slug":"correlation-congruence-for-knowledge","title":"Correlation Congruence for Knowledge Distillation","date":"2019-04-03","arxiv_id":"1904.01802","n_code_links":2,"syntology":null},{"paper":null,"slug":"m2kd-multi-model-and-multi-level-knowledge","title":"M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning","date":"2019-04-03","arxiv_id":"1904.01769","n_code_links":0,"syntology":null},{"paper":null,"slug":"making-neural-machine-reading-comprehension","title":"Making Neural Machine Reading Comprehension Faster","date":"2019-03-29","arxiv_id":"1904.00796","n_code_links":0,"syntology":null},{"paper":"/paper/improving-neural-architecture-search-image","slug":"improving-neural-architecture-search-image","title":"Improving Neural Architecture Search Image Classifiers via Ensemble Learning","date":"2019-03-14","arxiv_id":"1903.06236","n_code_links":1,"syntology":null},{"paper":null,"slug":"rectified-decision-trees-towards","title":"Rectified Decision Trees: Towards Interpretability, Compression and Empirical Soundness","date":"2019-03-14","arxiv_id":"1903.05965","n_code_links":0,"syntology":null},{"paper":null,"slug":"refine-and-distill-exploiting-cycle","title":"Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation","date":"2019-03-11","arxiv_id":"1903.04202","n_code_links":0,"syntology":null},{"paper":"/paper/structured-knowledge-distillation-for","slug":"structured-knowledge-distillation-for","title":"Structured Knowledge Distillation for Dense Prediction","date":"2019-03-11","arxiv_id":"1903.04197","n_code_links":1,"syntology":{"ran":5,"of":5,"n_ran_checked":2,"n_instrument":3,"unverified":0,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["irfanICMLL/structure_knowledge_distillation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/seizurenet-a-deep-convolutional-neural","slug":"seizurenet-a-deep-convolutional-neural","title":"SeizureNet: Multi-Spectral Deep Feature Learning for Seizure Type Classification","date":"2019-03-08","arxiv_id":"1903.03232","n_code_links":3,"syntology":null},{"paper":null,"slug":"progressive-label-distillation-learning-input","title":"Progressive Label Distillation: Learning Input-Efficient Deep Neural Networks","date":"2019-01-26","arxiv_id":"1901.09135","n_code_links":0,"syntology":null},{"paper":null,"slug":"unsupervised-learning-of-neural-networks-to","title":"Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract)","date":"2019-01-21","arxiv_id":"1901.07538","n_code_links":0,"syntology":null},{"paper":null,"slug":"stealing-neural-networks-via-timing-side","title":"Stealing Neural Networks via Timing Side Channels","date":"2018-12-31","arxiv_id":"1812.11720","n_code_links":0,"syntology":null},{"paper":"/paper/feature-matters-a-stage-by-stage-approach-for","slug":"feature-matters-a-stage-by-stage-approach-for","title":"An Embarrassingly Simple Approach for Knowledge Distillation","date":"2018-12-05","arxiv_id":"1812.01819","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":3,"n_instrument":0,"unverified":0,"pointer_only":3,"phrase":"3 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; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/knowledge-distillation-from-few-samples","slug":"knowledge-distillation-from-few-samples","title":"Few Sample Knowledge Distillation for Efficient Network Compression","date":"2018-12-05","arxiv_id":"1812.01839","n_code_links":1,"syntology":null},{"paper":null,"slug":"accelerating-large-scale-knowledge","title":"Accelerating Large Scale Knowledge Distillation via Dynamic Importance Sampling","date":"2018-12-03","arxiv_id":"1812.00914","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-with-feature-maps-for","title":"Knowledge Distillation with Feature Maps for Image Classification","date":"2018-12-03","arxiv_id":"1812.00660","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-specialize-with-knowledge","title":"Learning to Specialize with Knowledge Distillation for Visual Question Answering","date":"2018-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-compressing-u-net-using-knowledge","title":"On Compressing U-net Using Knowledge Distillation","date":"2018-12-01","arxiv_id":"1812.00249","n_code_links":0,"syntology":null},{"paper":null,"slug":"expandnets-exploiting-linear-redundancy-to","title":"ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks","date":"2018-11-26","arxiv_id":"1811.10495","n_code_links":0,"syntology":null},{"paper":null,"slug":"graph-adaptive-pruning-for-efficient","title":"Graph-Adaptive Pruning for Efficient Inference of Convolutional Neural Networks","date":"2018-11-21","arxiv_id":"1811.08589","n_code_links":0,"syntology":null},{"paper":null,"slug":"factorized-distillation-training-holistic","title":"Factorized Distillation: Training Holistic Person Re-identification Model by Distilling an Ensemble of Partial ReID Models","date":"2018-11-20","arxiv_id":"1811.08073","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-referenced-deep-learning","title":"Self-Referenced Deep Learning","date":"2018-11-19","arxiv_id":"1811.07598","n_code_links":0,"syntology":null},{"paper":null,"slug":"private-model-compression-via-knowledge","title":"Private Model Compression via Knowledge Distillation","date":"2018-11-13","arxiv_id":"1811.05072","n_code_links":0,"syntology":null},{"paper":null,"slug":"sequence-level-knowledge-distillation-for","title":"Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition","date":"2018-11-12","arxiv_id":"1811.04531","n_code_links":0,"syntology":null},{"paper":"/paper/cogni-net-cognitive-feature-learning-through","slug":"cogni-net-cognitive-feature-learning-through","title":"Cogni-Net: Cognitive Feature Learning through Deep Visual Perception","date":"2018-11-01","arxiv_id":"1811.00201","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-closer-look-at-deep-learning-heuristics-1","title":"A Closer Look at Deep Learning Heuristics: Learning rate restarts, Warmup and Distillation","date":"2018-10-29","arxiv_id":"1810.13243","n_code_links":0,"syntology":null},{"paper":"/paper/fast-neural-architecture-search-of-compact","slug":"fast-neural-architecture-search-of-compact","title":"Fast Neural Architecture Search of Compact Semantic Segmentation Models via Auxiliary Cells","date":"2018-10-25","arxiv_id":"1810.10804","n_code_links":4,"syntology":null},{"paper":null,"slug":"ktan-knowledge-transfer-adversarial-network","title":"KTAN: Knowledge Transfer Adversarial Network","date":"2018-10-18","arxiv_id":"1810.08126","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-from-few-samples-1","title":"Knowledge Distillation from Few Samples","date":"2018-09-27","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/ranking-distillation-learning-compact-ranking","slug":"ranking-distillation-learning-compact-ranking","title":"Ranking Distillation: Learning Compact Ranking Models With High Performance for Recommender System","date":"2018-09-19","arxiv_id":"1809.07428","n_code_links":1,"syntology":null},{"paper":"/paper/real-time-joint-semantic-segmentation-and","slug":"real-time-joint-semantic-segmentation-and","title":"Real-Time Joint Semantic Segmentation and Depth Estimation Using Asymmetric Annotations","date":"2018-09-13","arxiv_id":"1809.04766","n_code_links":4,"syntology":{"ran":6,"of":6,"n_ran_checked":0,"n_instrument":6,"unverified":0,"pointer_only":6,"phrase":"6 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; 6 where Syntology's instrument failed) · 0 unverified","official":{"repos":["DrSleep/multi-task-refinenet"],"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":["listed","official"]}}},{"paper":null,"slug":"label-denoising-with-large-ensembles-of","title":"Label Denoising with Large Ensembles of Heterogeneous Neural Networks","date":"2018-09-12","arxiv_id":"1809.04403","n_code_links":0,"syntology":null},{"paper":null,"slug":"rapid-training-of-very-large-ensembles-of","title":"MotherNets: Rapid Deep Ensemble Learning","date":"2018-09-12","arxiv_id":"1809.04270","n_code_links":0,"syntology":null},{"paper":"/paper/rdpd-rich-data-helps-poor-data-via-imitation","slug":"rdpd-rich-data-helps-poor-data-via-imitation","title":"RDPD: Rich Data Helps Poor Data via Imitation","date":"2018-09-06","arxiv_id":"1809.01921","n_code_links":1,"syntology":null},{"paper":null,"slug":"lifelong-learning-via-progressive","title":"Lifelong Learning via Progressive Distillation and Retrospection","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"whole-slide-mitosis-detection-in-he-breast","title":"Whole-Slide Mitosis Detection in H&E Breast Histology Using PHH3 as a Reference to Train Distilled Stain-Invariant Convolutional Networks","date":"2018-08-17","arxiv_id":"1808.05896","n_code_links":0,"syntology":null},{"paper":null,"slug":"cooperative-denoising-for-distantly","title":"Cooperative Denoising for Distantly Supervised Relation Extraction","date":"2018-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/self-supervised-knowledge-distillation-using","slug":"self-supervised-knowledge-distillation-using","title":"Self-supervised Knowledge Distillation Using Singular Value Decomposition","date":"2018-07-18","arxiv_id":"1807.06819","n_code_links":3,"syntology":null},{"paper":"/paper/distillation-techniques-for-pseudo-rehearsal","slug":"distillation-techniques-for-pseudo-rehearsal","title":"Distillation Techniques for Pseudo-rehearsal Based Incremental Learning","date":"2018-07-08","arxiv_id":"1807.02799","n_code_links":1,"syntology":null},{"paper":"/paper/channel-gating-neural-networks","slug":"channel-gating-neural-networks","title":"Channel Gating Neural Networks","date":"2018-05-29","arxiv_id":"1805.12549","n_code_links":1,"syntology":{"ran":2,"of":4,"n_ran_checked":0,"n_instrument":2,"unverified":2,"pointer_only":2,"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) · 2 unverified","official":null}},{"paper":"/paper/knowledge-distillation-with-adversarial","slug":"knowledge-distillation-with-adversarial","title":"Knowledge Distillation with Adversarial Samples Supporting Decision Boundary","date":"2018-05-15","arxiv_id":"1805.05532","n_code_links":1,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":1,"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) · 0 unverified","official":{"repos":["bhheo/BSS_distillation"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"few-shot-learning-of-neural-networks-from","title":"Few-shot learning of neural networks from scratch by pseudo example optimization","date":"2018-02-08","arxiv_id":"1802.03039","n_code_links":0,"syntology":null},{"paper":"/paper/faster-gaze-prediction-with-dense-networks","slug":"faster-gaze-prediction-with-dense-networks","title":"Faster gaze prediction with dense networks and Fisher pruning","date":"2018-01-17","arxiv_id":"1801.05787","n_code_links":2,"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":null}},{"paper":null,"slug":"generation-and-consolidation-of-recollections","title":"Generation and Consolidation of Recollections for Efficient Deep Lifelong Learning","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/learning-deep-and-compact-models-for-gesture","slug":"learning-deep-and-compact-models-for-gesture","title":"Learning Deep and Compact Models for Gesture Recognition","date":"2017-12-29","arxiv_id":"1712.10136","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-efficient-object-detection-models","title":"Learning Efficient Object Detection Models with Knowledge Distillation","date":"2017-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/microexpnet-an-extremely-small-and-fast-model","slug":"microexpnet-an-extremely-small-and-fast-model","title":"MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Face Images","date":"2017-11-19","arxiv_id":"1711.07011","n_code_links":3,"syntology":null},{"paper":null,"slug":"apprentice-using-knowledge-distillation","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","date":"2017-11-15","arxiv_id":"1711.05852","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-for-bilingual","title":"Knowledge Distillation for Bilingual Dictionary Induction","date":"2017-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tip-typifying-the-interpretability-of","title":"TIP: Typifying the Interpretability of Procedures","date":"2017-06-09","arxiv_id":"1706.02952","n_code_links":0,"syntology":null},{"paper":null,"slug":"knowledge-distillation-using-unlabeled","title":"Knowledge distillation using unlabeled mismatched images","date":"2017-03-21","arxiv_id":"1703.07131","n_code_links":0,"syntology":null},{"paper":"/paper/collaborative-deep-reinforcement-learning","slug":"collaborative-deep-reinforcement-learning","title":"Collaborative Deep Reinforcement Learning","date":"2017-02-19","arxiv_id":"1702.05796","n_code_links":1,"syntology":null},{"paper":null,"slug":"neural-machine-translation-from-simplified","title":"Neural Machine Translation from Simplified Translations","date":"2016-12-19","arxiv_id":"1612.06139","n_code_links":0,"syntology":null},{"paper":null,"slug":"in-teacher-we-trust-learning-compressed","title":"In Teacher We Trust: Learning Compressed Models for Pedestrian Detection","date":"2016-12-01","arxiv_id":"1612.00478","n_code_links":0,"syntology":null},{"paper":"/paper/sequence-level-knowledge-distillation","slug":"sequence-level-knowledge-distillation","title":"Sequence-Level Knowledge Distillation","date":"2016-06-25","arxiv_id":"1606.07947","n_code_links":6,"syntology":{"ran":1,"of":2,"n_ran_checked":1,"n_instrument":0,"unverified":1,"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) · 1 unverified","official":{"repos":["harvardnlp/nmt-android","harvardnlp/seq2seq-attn"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"adapting-models-to-signal-degradation-using","title":"Adapting Models to Signal Degradation using Distillation","date":"2016-04-01","arxiv_id":"1604.00433","n_code_links":0,"syntology":null},{"paper":"/paper/distilling-the-knowledge-in-a-neural-network","slug":"distilling-the-knowledge-in-a-neural-network","title":"Distilling the Knowledge in a Neural Network","date":"2015-03-09","arxiv_id":"1503.02531","n_code_links":64,"syntology":{"ran":23,"of":37,"n_ran_checked":14,"n_instrument":9,"unverified":14,"pointer_only":11,"phrase":"23 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 6 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified","official":null}}],"record_sha256":"6480370ecaac88a64e36f9b306f286056e190fc1df3926d7fbcf65eea5c975c9","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}