{"id":"W4210501868","doi":"10.1016/j.saa.2022.120961","title":"Overfitting One-Dimensional convolutional neural networks for Raman spectra identification","year":2022,"lang":"en","type":"article","venue":"Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy","topic":"Spectroscopy Techniques in Biomedical and Chemical Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Overfitting; Computer science; Convolutional neural network; Mobile device; Identification (biology); Raman spectroscopy; Process (computing); Artificial intelligence; Spectrometer; Pixel; Pattern recognition (psychology); Matching (statistics); Artificial neural network; Mathematics; Optics","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006397357,0.0004623535,0.0004015247,0.0001855745,0.0007707988,0.0001361505,0.0006415587,0.000217621,0.0002170301],"category_scores_gemma":[0.0001639373,0.000506518,0.0003701798,0.0004221855,0.0004197646,0.00001510099,0.0007207931,0.0005803506,0.000002375322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001725117,"about_ca_system_score_gemma":0.0001508277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001157048,"about_ca_topic_score_gemma":0.000003320722,"domain_scores_codex":[0.9959819,0.0001997705,0.0005996312,0.001294577,0.0008512062,0.00107293],"domain_scores_gemma":[0.9985697,0.00005053626,0.0002302448,0.0006702422,0.0001241245,0.0003551767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006818617,0.0003136272,0.0000914518,0.00002641301,0.0001709675,0.00001904362,0.000009485992,0.0000535901,0.9883401,0.003955335,0.006225807,0.0001123435],"study_design_scores_gemma":[0.001302891,0.0014517,0.0001445788,0.00001273049,0.00008504679,0.0001647603,0.0000284867,0.008179096,0.9644377,0.002975487,0.0205932,0.0006243065],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8084936,0.00267079,0.1812116,0.003699996,0.0005975253,0.001785004,0.0002644024,0.0001950521,0.001082],"genre_scores_gemma":[0.9861739,0.0001372668,0.009242451,0.001433045,0.0005819354,0.000537203,0.001515382,0.0001002373,0.0002785316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1776804,"threshold_uncertainty_score":0.9997386,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01069080248704618,"score_gpt":0.2860646786343092,"score_spread":0.275373876147263,"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."}}