{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00003661876,0.0001910794,0.0001870338,0.00007828172,0.00009809766,0.0001980662,0.0006458369,0.0002112638,0.000312067],"category_scores_gemma":[0.00002372786,0.0001657029,0.0001032237,0.000231384,0.000007234949,0.0003048589,0.00006767717,0.0002375901,0.001781032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001432525,"about_ca_system_score_gemma":0.00006385842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004845915,"about_ca_topic_score_gemma":0.0003718506,"domain_scores_codex":[0.9988639,0.00002858708,0.0002029307,0.0004658657,0.0002487327,0.0001900277],"domain_scores_gemma":[0.9993436,0.00002804615,0.0000961826,0.0003079537,0.00008501101,0.0001392077],"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":[0.0001265148,0.0006984524,0.0005669237,0.000810688,0.0001583736,0.0001954094,0.02184422,0.0001248129,0.0690052,0.005119545,0.1329008,0.7684491],"study_design_scores_gemma":[0.001627063,0.0002468847,0.01152597,0.0004824536,0.00006576168,0.0000101048,0.003090434,0.7561897,0.1035397,0.001591209,0.1195201,0.002110647],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007981309,0.0004313248,0.8365969,0.001571778,0.004515104,0.0006206717,0.000009931905,0.001273145,0.1469998],"genre_scores_gemma":[0.07848319,0.0003758184,0.8178732,0.005123138,0.0005507265,0.0002125583,0.003221757,0.0001261321,0.09403349],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7663385,"threshold_uncertainty_score":0.9989962,"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."}}