{"id":"W3108981297","doi":"10.1098/rspa.2021.0068","title":"Inductive biases for deep learning of higher-level cognition","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Royal Society A Mathematical Physical and Engineering Sciences","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":268,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Exploit; Heuristics; Human intelligence; Generalization; Computer science; Artificial intelligence; Inductive bias; Cognitive science; Cognition; Animal cognition; Machine learning; Cognitive psychology; Task (project management); Psychology; Multi-task learning; Epistemology","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":[0.0001810046,0.00007450262,0.0001373745,0.00001412963,0.0003162033,0.00002236352,0.0001720561,0.00001497486,0.000005499027],"category_scores_gemma":[0.0003576966,0.00004960776,0.000122278,0.0002817789,0.0002375726,0.00008842372,0.0001585167,0.0001345772,1.50118e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001114004,"about_ca_system_score_gemma":0.000005137277,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001319708,"about_ca_topic_score_gemma":6.524004e-9,"domain_scores_codex":[0.9992944,0.000004360728,0.000116658,0.0001724242,0.0002786664,0.0001334613],"domain_scores_gemma":[0.9994096,0.0004165409,0.00009558077,0.00002044044,0.00003238339,0.00002541808],"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":[0.00001628083,0.0002161091,0.00005884298,0.0004075789,0.00001291918,3.043084e-8,0.001221518,0.01341652,0.7781829,0.2056955,0.00005817572,0.0007136884],"study_design_scores_gemma":[0.0001435007,0.000296377,0.000539885,0.00004738104,0.00002562258,0.000001578272,0.0005204282,0.8792239,0.07170337,0.04736052,0.00004040098,0.00009701285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985515,0.000006988295,0.0007314708,0.000197457,0.00006110202,0.0001458162,0.000008645523,0.00002265174,0.0002743258],"genre_scores_gemma":[0.9988,0.00000114072,0.0009770172,0.00003292529,0.00003586282,0.00003728621,1.698035e-7,0.000005516783,0.0001100196],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8658074,"threshold_uncertainty_score":0.2432012,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03973156424526133,"score_gpt":0.2488793072862359,"score_spread":0.2091477430409745,"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."}}