{"id":"W4392928102","doi":"10.32920/25417270","title":"Information Theoretic Measures Applied to Deep Learning Models","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Mutual information; Computer science; Maximization; Artificial intelligence; Deep learning; Machine learning; Architecture; Interaction information; Information theory; Data mining; Mathematics; Statistics","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":[0.006272666,0.001253491,0.000998158,0.00254775,0.0004296805,0.002220976,0.001234166,0.00140989,0.002054713],"category_scores_gemma":[0.02304894,0.000607896,0.000915458,0.001705885,0.002115501,0.003887474,0.002609414,0.002991328,0.0004567617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001719499,"about_ca_system_score_gemma":0.001084788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009830166,"about_ca_topic_score_gemma":0.0007810869,"domain_scores_codex":[0.9964619,0.001717988,0.0002731788,0.0004076823,0.001007737,0.0001314423],"domain_scores_gemma":[0.9902242,0.00683684,0.0008211962,0.00123252,0.0007157033,0.000169462],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005599958,0.00004991071,0.0007608366,0.0002586245,0.0001719455,0.00009820099,0.00008532419,0.2691915,0.003048721,0.6576062,0.002032922,0.06663974],"study_design_scores_gemma":[0.000006088823,0.00004045791,0.0002183926,0.00004203176,0.00001674877,0.00005124783,0.00001029807,0.6452228,0.002560836,0.3494594,0.002350429,0.00002128559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004633573,0.001087911,0.9907222,0.0004169023,0.00008716565,0.00002374803,0.0000878592,0.0002125214,0.002728114],"genre_scores_gemma":[0.586831,0.003061886,0.4033008,0.0004633183,0.0006281929,0.0003428863,0.0005075153,0.0003336137,0.004530677],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006272666,"threshold_uncertainty_score":0.03317338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02582926654290517,"score_gpt":0.2557815616739663,"score_spread":0.2299522951310611,"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."}}