{"id":"W3195180572","doi":"10.1109/wacv56688.2023.00529","title":"Serf: Towards better training of deep neural networks using log-Softplus ERror activation Function","year":2023,"lang":"en","type":"article","venue":"2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Activation function; Artificial intelligence; Regularization (linguistics); Artificial neural network; Monotonic function; Pattern recognition (psychology); Machine learning; 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":[0.002908769,0.001583383,0.0009210049,0.0007726081,0.0003411428,0.0007238073,0.001936368,0.002029556,0.003633079],"category_scores_gemma":[0.006015085,0.0005922977,0.0007705996,0.0004947541,0.0007742565,0.002049317,0.001468639,0.002612725,0.001386549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008048318,"about_ca_system_score_gemma":0.001482279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004086202,"about_ca_topic_score_gemma":0.006621227,"domain_scores_codex":[0.9994703,0.0001818152,0.00003454366,0.00009311502,0.0001401379,0.00008011049],"domain_scores_gemma":[0.9987659,0.0005933136,0.00008381466,0.0001677258,0.0003223484,0.00006686711],"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":[0.0002428952,0.0001871592,0.001340027,0.0002080569,0.00009333177,0.0001539443,0.0001262655,0.6987696,0.009216529,0.009348447,0.005972353,0.2743414],"study_design_scores_gemma":[0.000007836539,0.00003836262,0.00008327267,0.00001255426,0.000003552467,0.00002279655,0.000006877534,0.996159,0.001621845,0.001531919,0.0005079773,0.000004086853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02803233,0.0006563262,0.9657669,0.0003362822,0.00007332682,0.00006537024,0.0001069051,0.002972462,0.001990105],"genre_scores_gemma":[0.4599517,0.0004719538,0.530527,0.0006403134,0.00007524719,0.0002877349,0.0007342489,0.000652873,0.006658954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004086202,"threshold_uncertainty_score":0.01538318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06425871713562263,"score_gpt":0.3228914887893151,"score_spread":0.2586327716536924,"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."}}