{"id":"W4236821994","doi":"10.22215/etd/2020-14357","title":"Multi-scale Deep Nearest Neighbors","year":2020,"lang":"en","type":"dissertation","venue":"","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Embedding; Margin (machine learning); Cluster analysis; k-nearest neighbors algorithm; Artificial intelligence; Pattern recognition (psychology); Classifier (UML); Sample space; Differentiable function; Space (punctuation); Scale (ratio); Computer science; Feature vector; Sample (material); Mathematics; Algorithm; Machine learning; Geography; Physics; Pure mathematics; Cartography","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":[0.0007039194,0.0006120892,0.001135443,0.001053038,0.000622606,0.001368417,0.001266149,0.001064956,0.005848403],"category_scores_gemma":[0.002401718,0.0003900489,0.0007671111,0.001330041,0.0004207581,0.002174205,0.001444336,0.0009391271,0.00281396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00071332,"about_ca_system_score_gemma":0.0006761202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006413461,"about_ca_topic_score_gemma":0.01170949,"domain_scores_codex":[0.9989441,0.00008522528,0.00005897294,0.0003311427,0.0004513201,0.0001292567],"domain_scores_gemma":[0.9990771,0.0001531971,0.0000823684,0.0002245148,0.0004071538,0.00005560647],"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":[0.0002633036,0.0002129136,0.002824557,0.0002269243,0.0001473874,0.0001333247,0.0001487707,0.1060416,0.01373286,0.01392641,0.01812498,0.8442169],"study_design_scores_gemma":[0.00001860785,0.0001064752,0.00215655,0.00005293514,0.00003955976,0.0001851474,0.00008681714,0.9624458,0.00913095,0.01744918,0.008293869,0.00003417199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08463275,0.00453147,0.8850631,0.0006071314,0.0006392333,0.0001522505,0.001405086,0.002588318,0.02038064],"genre_scores_gemma":[0.7571158,0.00195017,0.2094105,0.0003516075,0.0002466397,0.000127088,0.002422686,0.000244044,0.02813147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006413461,"threshold_uncertainty_score":0.01956487,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0176580703285912,"score_gpt":0.2613767356172755,"score_spread":0.2437186652886843,"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."}}