{"id":"W2994861143","doi":"10.1109/ipta.2019.8936079","title":"Subtractive Perceptrons for Learning Images: A Preliminary Report","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; MNIST database; Perceptron; Artificial intelligence; Artificial neural network; Network topology; Machine learning; Deep learning; Benchmark (surveying); Task (project management); Pattern recognition (psychology)","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":[0.002603697,0.001051231,0.0007620059,0.0009224539,0.0002852551,0.001308744,0.001373256,0.001181851,0.010341],"category_scores_gemma":[0.00616751,0.0006483053,0.0009250151,0.001537445,0.0006648607,0.0025443,0.001148793,0.003165157,0.003891149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009627155,"about_ca_system_score_gemma":0.0007138783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005181354,"about_ca_topic_score_gemma":0.003600225,"domain_scores_codex":[0.9989904,0.0002888095,0.00005456887,0.0001700499,0.000428112,0.0000681646],"domain_scores_gemma":[0.9979856,0.0008450171,0.00005490692,0.0002373419,0.0007217351,0.0001552677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008358583,0.0008922814,0.001996547,0.0008913658,0.000302777,0.0003782725,0.0003036408,0.1271721,0.01687408,0.05914966,0.08126795,0.7099354],"study_design_scores_gemma":[0.00006873488,0.0005585821,0.001759731,0.0001287925,0.00008807958,0.0002524857,0.00009278036,0.8530685,0.02149396,0.04015017,0.08227056,0.00006768086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03445922,0.03426648,0.8790171,0.00620067,0.002326834,0.0003175957,0.001265857,0.004102108,0.03804412],"genre_scores_gemma":[0.3502834,0.03580407,0.4972774,0.002310486,0.003090428,0.000622438,0.007230803,0.001063994,0.102317],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.010341,"threshold_uncertainty_score":0.03459418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02487556330652957,"score_gpt":0.2982258250669944,"score_spread":0.2733502617604648,"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."}}