{"id":"W2119985666","doi":"","title":"Inferring Motor Programs from Images of Handwritten Digits","year":2005,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Overfitting; Computer science; Digit recognition; Artificial intelligence; Classifier (UML); Set (abstract data type); Pattern recognition (psychology); Class (philosophy); Numerical digit; Machine learning; Speech recognition; Artificial neural network; Mathematics","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":[0.0001843872,0.0004546523,0.0003020413,0.0004049892,0.0001867715,0.0004759174,0.0006653763,0.0006715305,0.002272932],"category_scores_gemma":[0.00121513,0.000479347,0.0005567133,0.0002734535,0.000536261,0.0007412473,0.0003558692,0.0008843977,0.0005255866],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005107723,"about_ca_system_score_gemma":0.0003647505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002073017,"about_ca_topic_score_gemma":0.005185487,"domain_scores_codex":[0.9998682,0.00001986639,0.000003863938,0.00005190844,0.00003878671,0.00001749285],"domain_scores_gemma":[0.9997299,0.0001171924,0.00004216916,0.00006256023,0.00002945488,0.00001869608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003621551,0.0001448461,0.00468048,0.000252426,0.00008497835,0.0007863849,0.0001735336,0.5893795,0.1031327,0.02951403,0.003346871,0.268142],"study_design_scores_gemma":[0.00001140007,0.00002367174,0.001763189,0.00001310815,0.00001075958,0.0001640484,0.00001753585,0.9624891,0.02190361,0.01202498,0.001563482,0.00001523037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1188304,0.0002589425,0.8737181,0.0003169255,0.00006403984,0.00006240037,0.000488457,0.00193853,0.004322026],"genre_scores_gemma":[0.8030175,0.0002533075,0.1910461,0.0001470269,0.00002962224,0.0000546474,0.000599272,0.000173022,0.004679661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002272932,"threshold_uncertainty_score":0.007603705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01644595604666064,"score_gpt":0.2193960317840821,"score_spread":0.2029500757374215,"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."}}