{"id":"W3198769081","doi":"10.1007/978-3-030-63591-6_12","title":"Comparing Regularization Techniques Applied to a Perceptron","year":2021,"lang":"en","type":"book-chapter","venue":"Springer proceedings in mathematics & statistics","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Overfitting; Regularization (linguistics); Computer science; Artificial neural network; Artificial intelligence; Perceptron; Machine learning; Deep neural networks; Multilayer perceptron","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002844163,0.00041452,0.0005932066,0.0002678253,0.0001187833,0.0004282885,0.0009019883,0.0002246245,0.00002838736],"category_scores_gemma":[0.00004418064,0.0004543071,0.00005719294,0.0001828549,0.0000500427,0.0001192773,0.0007171195,0.0004826181,0.00006147212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001815859,"about_ca_system_score_gemma":0.00006258937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002126778,"about_ca_topic_score_gemma":0.000009967676,"domain_scores_codex":[0.997721,0.000002526855,0.0007058127,0.0007156556,0.0004902844,0.0003646807],"domain_scores_gemma":[0.9986733,0.0000779912,0.0003583952,0.00047359,0.0002839778,0.0001327007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001163241,0.00003772452,0.000006651414,0.0002849481,0.00001237127,0.000007255439,0.0006760269,0.00002344484,0.0006531222,0.9875532,0.001726152,0.009017935],"study_design_scores_gemma":[0.0001573508,0.00005360306,0.00006590722,0.001247621,0.00005483694,0.00002129775,0.00006359524,0.02145813,0.001199976,0.9209037,0.05372044,0.001053566],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004303041,0.00003457928,0.7517052,0.0001418812,0.00007190306,0.0007661962,0.000013182,0.0002449323,0.2469791],"genre_scores_gemma":[0.002268868,0.0001152755,0.9446123,0.0001609201,0.0001629942,0.0001547926,0.0000283866,0.00009213296,0.05240429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1945748,"threshold_uncertainty_score":0.9997908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02507929566696502,"score_gpt":0.2531904974517191,"score_spread":0.2281112017847541,"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."}}