{"id":"W2986473551","doi":"10.1080/22020586.2019.12072983","title":"Mineralisation predictive targeting using TensorFlow (Google) deep neural networks","year":2019,"lang":"en","type":"article","venue":"ASEG Extended Abstracts","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Petro Geotech (Canada)","funders":"","keywords":"Artificial neural network; Python (programming language); Deep neural networks; Deep learning; Artificial intelligence; Shield; Computer science; Geology; Petrology; Operating system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.0004527321,0.001322451,0.0004127588,0.0008782269,0.000347554,0.0008845659,0.001221284,0.0005621639,0.005198391],"category_scores_gemma":[0.001478303,0.000370787,0.0007809764,0.0009655943,0.0003325871,0.001062591,0.0008103341,0.0009673951,0.001774673],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001153474,"about_ca_system_score_gemma":0.001294579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.04844844,"about_ca_topic_score_gemma":0.06145944,"domain_scores_codex":[0.9998028,0.00001729019,0.00001031239,0.00005834868,0.00007991566,0.00003129255],"domain_scores_gemma":[0.9996852,0.00006738491,0.00003986359,0.0000468074,0.0001411691,0.00001953956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002522128,0.0001047964,0.00450492,0.000205574,0.0001381954,0.0001399602,0.00008310856,0.6937633,0.009105519,0.004265241,0.03749125,0.249946],"study_design_scores_gemma":[0.000008864958,0.000009196155,0.0003201545,0.000005803583,0.000006170304,0.00001029494,0.000006773406,0.9931357,0.00262566,0.00183887,0.002024357,0.000008149665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1118931,0.001457518,0.7720852,0.001236815,0.0003956188,0.0001973031,0.0138293,0.08459479,0.01431032],"genre_scores_gemma":[0.6118941,0.0007655685,0.3489262,0.0003911618,0.0001026792,0.0002108693,0.02481876,0.002292871,0.01059783],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04844844,"threshold_uncertainty_score":0.09633291,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00971232987889054,"score_gpt":0.2166362563409481,"score_spread":0.2069239264620576,"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."}}