{"id":"W2605960745","doi":"10.1016/j.cmpb.2017.04.012","title":"Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification","year":2017,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"AI in cancer detection","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Multi-objective optimization; Autoencoder; Discriminative model; Pattern recognition (psychology); Sorting; Artificial intelligence; Encoder; Genetic algorithm; Pareto principle; Dimensionality reduction; Mean squared error; Artificial neural network; Reduction (mathematics); Algorithm; Machine learning; Mathematical optimization; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.002396126,0.0002201,0.0003308487,0.0002578433,0.0005226159,0.0002522091,0.0005807742,0.0001633678,0.000001213055],"category_scores_gemma":[0.00007048303,0.0001877232,0.00008715308,0.0003505714,0.0004398674,0.0005272055,0.0002799975,0.0002161981,7.263656e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009053663,"about_ca_system_score_gemma":0.00003920708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009963138,"about_ca_topic_score_gemma":0.00001547163,"domain_scores_codex":[0.9979395,0.0002899697,0.0004037063,0.000814691,0.0002164891,0.0003356945],"domain_scores_gemma":[0.998295,0.0001778402,0.0003423826,0.0008480388,0.0002076192,0.0001291391],"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":[0.0000397263,0.0001105521,0.002735876,0.00004799386,0.00003145081,0.000001879885,0.0007197103,0.00001318397,0.001567085,0.001522426,0.00005346792,0.9931567],"study_design_scores_gemma":[0.001694315,0.0007566568,0.134152,0.0001216161,0.0000261115,0.00005084279,0.0001117031,0.8468347,0.0007914394,0.008557696,0.006600207,0.0003026858],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008063685,0.0004778826,0.9861084,0.001759921,0.00254933,0.0008620577,0.000001907952,0.0001509043,0.00002589236],"genre_scores_gemma":[0.1413314,0.00006432641,0.8578719,0.00007154237,0.0003950283,0.0002259723,0.00001265162,0.00001250095,0.00001460478],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9928539,"threshold_uncertainty_score":0.7655132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1165761016700205,"score_gpt":0.4079050726891905,"score_spread":0.29132897101917,"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."}}