{"id":"W1902934009","doi":"10.48550/arxiv.1511.00363","title":"BinaryConnect: Training Deep Neural Networks with binary weights during propagations","year":2015,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1835,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research; Polytechnique Montréal","funders":"","keywords":"MNIST database; Computer science; Dropout (neural networks); Artificial neural network; Deep neural networks; Binary number; Invariant (physics); Computation; Range (aeronautics); Artificial intelligence; Permutation (music); Computer engineering; Simple (philosophy); Deep learning; Algorithm; Machine learning; Arithmetic; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008228401,0.001454648,0.0005106693,0.0005592203,0.0004292555,0.0008596482,0.002125291,0.001205034,0.00487252],"category_scores_gemma":[0.003568386,0.0005588676,0.000385521,0.0006826987,0.0007970823,0.001913313,0.001339342,0.001462455,0.001086482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008743082,"about_ca_system_score_gemma":0.001087668,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005799512,"about_ca_topic_score_gemma":0.009124857,"domain_scores_codex":[0.9996181,0.00007351786,0.00002495551,0.00009267622,0.0001401248,0.00005072362],"domain_scores_gemma":[0.9992695,0.0002679601,0.00008881347,0.0001801918,0.0001444301,0.00004904451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009366674,0.000364925,0.003310665,0.000439389,0.0001717258,0.0002485783,0.0002042695,0.3664436,0.03118281,0.01898459,0.02204304,0.5556697],"study_design_scores_gemma":[0.00006160573,0.0001391571,0.0004310865,0.00002598329,0.00002676678,0.00008951964,0.00001483842,0.9665002,0.02260403,0.00598904,0.004098406,0.0000193115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1164395,0.0009258366,0.856275,0.0004542668,0.000324956,0.000239468,0.0005819607,0.01617243,0.00858657],"genre_scores_gemma":[0.5688263,0.0004361843,0.416778,0.0005265774,0.00009493415,0.0003503539,0.001883342,0.001286151,0.009818088],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005799512,"threshold_uncertainty_score":0.01630026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01877200430149616,"score_gpt":0.2391499425125286,"score_spread":0.2203779382110324,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}