{"id":"W2909808664","doi":"10.48550/arxiv.1901.02064","title":"Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Dataflow; Joint (building); Quantization (signal processing); Computer science; Artificial neural network; Artificial intelligence; Deep neural networks; Computer vision; Engineering; Parallel computing; Structural 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":[0.0000962922,0.0002163664,0.0002867728,0.0001888778,0.0001519289,0.00004866898,0.0008210941,0.000176235,0.000002876711],"category_scores_gemma":[0.00002519228,0.0002514043,0.0001146417,0.0005117617,0.0000767635,0.0004006221,0.0007210493,0.0002612933,0.000002176953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006397385,"about_ca_system_score_gemma":0.0000635767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000134617,"about_ca_topic_score_gemma":0.0000186369,"domain_scores_codex":[0.9985828,0.00006089399,0.0002294217,0.0008385061,0.00005779117,0.0002305741],"domain_scores_gemma":[0.9978653,0.0003044608,0.000412673,0.001129068,0.0002016351,0.00008693027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001494785,0.00003630278,0.0005256977,0.00004775931,0.00001743484,0.000001350691,0.0000171165,0.8349119,0.00006000251,0.1635773,0.00004330611,0.0007468436],"study_design_scores_gemma":[0.0003900531,0.00003995018,0.001021334,0.00003633363,0.00004135197,7.141236e-7,0.000006606138,0.9751601,0.0002932689,0.02265789,0.0001196677,0.0002326972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04283269,0.00004767064,0.9556607,0.0001587587,0.0002619637,0.0008282347,0.00002784658,0.0001124231,0.0000697149],"genre_scores_gemma":[0.9759952,0.00006049626,0.02357156,0.00008190648,0.00005270479,0.000006288006,0.0001457621,0.00001754632,0.0000685566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9331625,"threshold_uncertainty_score":0.9999938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08036996745277143,"score_gpt":0.2082286006720327,"score_spread":0.1278586332192613,"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."}}