{"id":"W4408386736","doi":"10.1016/j.neuron.2025.02.006","title":"Interpretable deep learning for deconvolutional analysis of neural signals","year":2025,"lang":"en","type":"article","venue":"Neuron","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":5,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada); McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Army Research Office; National Institute on Deafness and Other Communication Disorders; Engineering and Physical Sciences Research Council; Faculty of Arts and Sciences; Human Frontier Science Program; National Institutes of Health; Brain and Behavior Research Foundation; Canada First Research Excellence Fund; FAS Division of Science, Harvard University; McGill University","keywords":"Computer science; Artificial intelligence; Artificial neural network; Deep learning; Salience (neuroscience); Machine learning; Neural decoding; Pattern recognition (psychology); Decoding methods","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":[],"consensus_categories":[],"category_scores_codex":[0.00009502919,0.00008453523,0.0001924761,0.0003091743,0.000110648,0.00002702512,0.0001385263,0.00003365686,0.0000764773],"category_scores_gemma":[0.0005864083,0.00008047306,0.0001832803,0.0007842783,0.00004341473,0.0001017898,0.00004938461,0.0001084345,0.000002081043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001901523,"about_ca_system_score_gemma":0.00001452765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008918863,"about_ca_topic_score_gemma":0.00001227799,"domain_scores_codex":[0.9991356,0.00007626288,0.0002102469,0.0002965931,0.0001162451,0.0001650564],"domain_scores_gemma":[0.9991108,0.0006043267,0.00009352979,0.0001204163,0.00004535992,0.00002561949],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001213028,0.00005121779,0.004417329,0.00002314558,0.00004879909,0.000001319957,0.00002423492,0.09440038,0.8863325,0.004686515,0.0001618024,0.009731415],"study_design_scores_gemma":[0.0001878229,0.0001306254,0.01501128,0.000005965585,0.0001811712,8.114889e-7,0.000006584075,0.9495308,0.03245285,0.000553431,0.00187098,0.00006764752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.97272,0.00002982227,0.02417809,0.0003077158,0.0004670703,0.0001782026,0.0000126632,0.00004697213,0.002059479],"genre_scores_gemma":[0.9971294,0.000009508885,0.00004476602,0.00082806,0.00001553691,0.00001705364,0.000009845197,0.000006452511,0.001939354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8551304,"threshold_uncertainty_score":0.3281596,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01832138834317143,"score_gpt":0.2777223668780648,"score_spread":0.2594009785348934,"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."}}