{"id":"W6999720541","doi":"","title":"Deep discriminant analysis based neural network pruning and compact architecture search","year":2021,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Pattern recognition (psychology); Artificial neural network; Feature (linguistics); Pruning; Linear discriminant analysis; Feature extraction","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","sts"],"consensus_categories":[],"category_scores_codex":[0.0007775984,0.0007448665,0.0009910887,0.0007422017,0.001540958,0.000567051,0.001075035,0.0005544267,0.0001161726],"category_scores_gemma":[0.0001963206,0.0006925275,0.0005702946,0.002326497,0.00005592865,0.0007622878,0.0002191663,0.001833581,0.00003215723],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001673889,"about_ca_system_score_gemma":0.00007570085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003250336,"about_ca_topic_score_gemma":0.002128029,"domain_scores_codex":[0.9948589,0.0008496919,0.0006993563,0.001578537,0.001034888,0.000978581],"domain_scores_gemma":[0.9972194,0.0004304704,0.0003844158,0.001082919,0.000381793,0.0005009982],"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":[0.0003637833,0.0004683159,0.0008395896,0.001088082,0.001857709,0.00079427,0.0002033418,0.0941911,0.04028703,0.01514203,0.00004177623,0.844723],"study_design_scores_gemma":[0.005455833,0.0011547,0.1017148,0.005603738,0.006573479,0.0002435055,0.002813776,0.6879383,0.1240885,0.03164828,0.02281455,0.009950492],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9846618,0.001106767,0.0007323737,0.0001511954,0.001216141,0.0006577608,0.0002050882,0.0003991569,0.01086978],"genre_scores_gemma":[0.9840298,0.0001139919,0.01161414,0.0004802089,0.0000710994,0.00004548084,0.002172232,0.0000903613,0.001382637],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8347725,"threshold_uncertainty_score":0.9997589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01863591916967442,"score_gpt":0.2543763853500434,"score_spread":0.235740466180369,"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."}}