{"id":"W4285407586","doi":"10.1109/cwit55308.2022.9817671","title":"Vector Quantization of Deep Convolutional Neural Networks With Learned Codebook","year":2022,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Codebook; Linde–Buzo–Gray algorithm; Vector quantization; Convolutional neural network; Quantization (signal processing); Computer science; Learning vector quantization; Artificial intelligence; Pattern recognition (psychology); Deep learning; Artificial neural network; Algorithm","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":[0.0009955339,0.0007617166,0.0008016267,0.0007613918,0.000271174,0.0008247274,0.001678768,0.0006350417,0.002049446],"category_scores_gemma":[0.005257577,0.0003034229,0.0003195879,0.001245834,0.0006049348,0.00206956,0.001118849,0.001479034,0.0007937076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001096941,"about_ca_system_score_gemma":0.0008616947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006680961,"about_ca_topic_score_gemma":0.008600056,"domain_scores_codex":[0.9992579,0.000128328,0.00005625195,0.0001416285,0.0003431149,0.00007291667],"domain_scores_gemma":[0.9987809,0.0004226707,0.0000947318,0.0003013182,0.0003530747,0.00004724948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002687703,0.0001108386,0.001193155,0.0002157733,0.00006361055,0.0001216884,0.00008760225,0.4374016,0.01578842,0.03897551,0.01123689,0.4945362],"study_design_scores_gemma":[0.00001379681,0.00004535816,0.0001476984,0.00001882097,0.000006316613,0.0000383999,0.00001184785,0.9812523,0.005904009,0.01050425,0.002045964,0.00001125346],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0234385,0.002113844,0.9685145,0.0002648055,0.000239335,0.00007735762,0.0004673649,0.002272615,0.002611725],"genre_scores_gemma":[0.6049008,0.001393195,0.3835405,0.0004242865,0.0001527407,0.000257066,0.002540181,0.0003161266,0.006475205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006680961,"threshold_uncertainty_score":0.01328415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01790890016029577,"score_gpt":0.2457396426820281,"score_spread":0.2278307425217323,"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."}}