{"id":"W2954582488","doi":"10.1109/cvpr.2019.00448","title":"Learning to Quantize Deep Networks by Optimizing Quantization Intervals With Task Loss","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Quantization (signal processing); Computer science; Deep learning; Task (project management); Reduction (mathematics); Residual neural network; Algorithm; Artificial intelligence; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002848336,0.00047601,0.0005098839,0.0001534732,0.0002054262,0.0005036811,0.001986369,0.000256993,0.00001708662],"category_scores_gemma":[0.00003865539,0.00042522,0.0001065327,0.0007612545,0.00004659357,0.0004134268,0.002561696,0.001043989,0.0001479297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001180141,"about_ca_system_score_gemma":0.00006060083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003961052,"about_ca_topic_score_gemma":0.00002872984,"domain_scores_codex":[0.9969072,0.0001487096,0.0005208303,0.001437473,0.0003929507,0.0005928787],"domain_scores_gemma":[0.9973948,0.0002596815,0.0004412294,0.00146913,0.0002257547,0.0002094038],"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":[0.00001247892,0.00002666208,0.0003876357,0.00002333787,0.00002956052,0.000003186407,0.0002720389,0.98289,0.0001242996,0.00534999,0.001496671,0.009384206],"study_design_scores_gemma":[0.0001822672,0.0001390199,0.00008443187,0.0001978577,0.00001589675,0.00001177678,0.0000412635,0.9941583,0.0002773123,0.0004256788,0.003856919,0.0006092779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003488824,0.0002717689,0.9915234,0.001409942,0.0004403819,0.00112375,0.000002367552,0.0007990458,0.0009404765],"genre_scores_gemma":[0.5998818,0.0001952578,0.397362,0.0008937751,0.0001219894,0.0001898363,0.00009351616,0.0000671753,0.001194673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5963929,"threshold_uncertainty_score":0.9998199,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0158344127692933,"score_gpt":0.2701146273165077,"score_spread":0.2542802145472144,"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."}}