{"id":"W2795231815","doi":"10.7287/peerj.preprints.26818v1","title":"A Deep Learning algorithm for accurate and fast identification of coral reef fishes in underwater videos","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Ichthyology and Marine Biology","field":"Environmental Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Identification (biology); Underwater; Task (project management); Computer science; Convolutional neural network; Artificial intelligence; Coral reef; Fish <Actinopterygii>; Coral reef fish; Artificial neural network; Machine learning; Fishery; Algorithm; Ecology; Oceanography; Biology; Engineering; Geology","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":[0.0006062785,0.0008140695,0.0004092956,0.0007155904,0.0003183387,0.0004161786,0.0008699524,0.0007337456,0.001721374],"category_scores_gemma":[0.001371035,0.0003709154,0.0004009842,0.0005427131,0.0003331994,0.000721839,0.0006706445,0.0009859481,0.0007309282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007530273,"about_ca_system_score_gemma":0.0008729571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01058648,"about_ca_topic_score_gemma":0.01050211,"domain_scores_codex":[0.9997504,0.00002719097,0.00001958229,0.00008288821,0.00008101283,0.0000389417],"domain_scores_gemma":[0.9996951,0.0000804237,0.00004273944,0.00003318589,0.0001309513,0.00001761664],"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":[0.0001074842,0.0001056176,0.001578282,0.00009475997,0.00006650952,0.0001153158,0.00005656057,0.1032402,0.03180081,0.002763646,0.006919742,0.8531511],"study_design_scores_gemma":[0.000009377687,0.0000411492,0.0008971083,0.00001629874,0.00001410476,0.00006340442,0.000009935113,0.9855192,0.009823222,0.001126423,0.00246931,0.00001047242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02268729,0.0003516898,0.9726768,0.0001628613,0.00008731548,0.00007540803,0.0002102324,0.002432746,0.001315575],"genre_scores_gemma":[0.2722765,0.0004185372,0.7179895,0.0002686466,0.00004890853,0.000241196,0.000805654,0.0001294861,0.007821549],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01058648,"threshold_uncertainty_score":0.02104968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01652111224957585,"score_gpt":0.2613699842518764,"score_spread":0.2448488720023005,"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."}}