{"id":"W2895260923","doi":"10.1007/978-3-030-01237-3_25","title":"Constraint-Aware Deep Neural Network Compression","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Agence Nationale de la Recherche","keywords":"Computer science; Deep learning; Artificial neural network; Deep neural networks; Software deployment; Artificial intelligence; Simulated annealing; Compression (physics); Constraint (computer-aided design); Mathematical optimization; Machine learning; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004600285,0.0006983436,0.0006129169,0.0003781651,0.0006337446,0.0004574689,0.004860347,0.0003801977,0.00009484779],"category_scores_gemma":[0.00003777675,0.0006402271,0.0001597439,0.0009319649,0.001824413,0.0006989249,0.002477527,0.001104836,0.0001548284],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002331558,"about_ca_system_score_gemma":0.0002348459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003561675,"about_ca_topic_score_gemma":0.00005585709,"domain_scores_codex":[0.9951317,0.00005185071,0.0006616352,0.002108951,0.0009469943,0.001098826],"domain_scores_gemma":[0.9959766,0.0007160732,0.0004540196,0.002212069,0.0003282244,0.0003130396],"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":[0.000005774043,0.00001927836,0.00003177411,0.00001555851,0.000008184481,0.00008270727,0.0001900789,0.2991725,0.00005637453,0.01679939,0.0002382379,0.6833801],"study_design_scores_gemma":[0.0001699896,0.0001086538,0.00005512047,0.0002076209,0.000005869894,0.0001445039,8.418954e-8,0.780871,0.0001873406,0.2139417,0.003697504,0.0006106495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004725565,0.0004786932,0.9928445,0.0009516373,0.002273878,0.0006113935,0.000005054462,0.0004145869,0.002373019],"genre_scores_gemma":[0.1600204,0.00006701352,0.8309932,0.005241374,0.003116931,0.00004021946,0.0000219169,0.00008915557,0.0004097981],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6827695,"threshold_uncertainty_score":0.9996049,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0192100646565952,"score_gpt":0.26223441128314,"score_spread":0.2430243466265448,"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."}}