{"id":"W4382652027","doi":"10.1101/2023.06.28.546924","title":"Learning better with Dale’s Law: A Spectral Perspective","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Recurrent neural network; Singular value decomposition; Computer science; Artificial neural network; Artificial intelligence; Feed forward; Perspective (graphical); Singular value; Constraint (computer-aided design); Law; Mathematics; Engineering; Physics","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":[0.00241191,0.0005424473,0.0006593802,0.0007601847,0.0004370831,0.002229318,0.001211268,0.00150108,0.002993911],"category_scores_gemma":[0.01353571,0.0003750258,0.000408274,0.0003112873,0.002909433,0.005543857,0.001616421,0.00208071,0.0005999011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006763699,"about_ca_system_score_gemma":0.0005335128,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001058611,"about_ca_topic_score_gemma":0.0008079435,"domain_scores_codex":[0.9990815,0.0003116594,0.00006746462,0.0002054224,0.0002482549,0.00008582044],"domain_scores_gemma":[0.9943209,0.003012419,0.0005800338,0.001061857,0.000731196,0.000293612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002191834,0.0002515305,0.006798205,0.0002929511,0.0001634152,0.0003145892,0.0005796721,0.4652037,0.0262351,0.3604955,0.004243296,0.1352028],"study_design_scores_gemma":[0.00001353584,0.0001117538,0.0009538858,0.00003543477,0.00001083246,0.00008253198,0.0000757825,0.7833648,0.003568458,0.2106214,0.001133452,0.00002814844],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1984446,0.00134392,0.775569,0.005416466,0.0002129996,0.00005969663,0.0001105988,0.0008259131,0.01801684],"genre_scores_gemma":[0.9461278,0.00038188,0.05044438,0.0005851862,0.0001188962,0.0000397749,0.00005903912,0.0000914517,0.002151635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002993911,"threshold_uncertainty_score":0.01275557,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02141940845334666,"score_gpt":0.2266716778410704,"score_spread":0.2052522693877237,"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."}}