{"id":"W2042871988","doi":"10.3758/s13420-011-0050-6","title":"Predicting shifts in generalization gradients with perceptrons","year":2011,"lang":"en","type":"article","venue":"Learning & Behavior","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Generalization; Stimulus generalization; Psychology; Perceptron; Set (abstract data type); Cognitive psychology; Artificial intelligence; Artificial neural network; Stimulus (psychology); Perception; Machine learning; Pattern recognition (psychology); Computer science; Neuroscience; Mathematics","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":[0.00007328383,0.00007985607,0.00006980381,0.00005802631,0.000131829,0.00003432999,0.0002676708,0.0000269669,0.0000221039],"category_scores_gemma":[0.000004146295,0.00006962261,0.00001864715,0.0003218538,0.00002053001,0.0002333743,0.00006549995,0.0001736261,0.00001729467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002089551,"about_ca_system_score_gemma":0.00001025233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001808866,"about_ca_topic_score_gemma":0.0001131839,"domain_scores_codex":[0.9992802,0.00004028135,0.0001169683,0.0002480262,0.0001145529,0.0002000421],"domain_scores_gemma":[0.9996669,0.000009336887,0.00005657667,0.0001947436,0.0000204577,0.00005202127],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001956996,0.00008861448,0.9784554,0.000001113473,0.000001274367,0.00001187195,0.001999105,0.001367848,0.001215805,0.002541238,0.00001448885,0.01430123],"study_design_scores_gemma":[0.0001587158,0.00006880362,0.9823458,0.00001801083,0.000007559523,0.000005619706,0.00003739769,0.01689712,0.0001237828,0.00002414996,0.0002053441,0.0001077198],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9556473,0.000009312439,0.04367314,0.00003845739,0.00005165904,0.0001436851,4.148008e-7,0.0001417427,0.0002942453],"genre_scores_gemma":[0.9855291,0.000003681455,0.01410293,0.00003506312,0.00002734497,0.00009216707,0.000004536122,0.000009991103,0.0001951802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02988177,"threshold_uncertainty_score":0.2839127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02667608136260416,"score_gpt":0.2445752799376097,"score_spread":0.2178991985750056,"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."}}