{"id":"W3018600685","doi":"10.48550/arxiv.2004.12058","title":"NullSpaceNet: Nullspace Convoluional Neural Network with Differentiable Loss Function","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Differentiable function; Separable space; Computer science; Reduction (mathematics); Inference; Function (biology); Interpretation (philosophy); Feature (linguistics); Algorithm; Mathematics; Artificial intelligence; Point (geometry); Artificial neural network; Pattern recognition (psychology); Mathematical analysis; Geometry","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":[0.00007021912,0.0005060586,0.0004419055,0.00009639697,0.0003426546,0.0001620822,0.001699625,0.000246916,0.00005283463],"category_scores_gemma":[0.000007538425,0.0005315901,0.0001783732,0.001147577,0.0001871348,0.0004502764,0.001972742,0.0009677396,0.0001343446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001781735,"about_ca_system_score_gemma":0.0001619112,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003633773,"about_ca_topic_score_gemma":0.00006605552,"domain_scores_codex":[0.9971331,0.0001301968,0.0002099189,0.001724248,0.0001806074,0.0006219108],"domain_scores_gemma":[0.9975561,0.000143829,0.000373958,0.001400385,0.0001722106,0.0003534454],"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":[0.0001104969,0.00005307019,0.003908242,0.00003125234,0.00008838624,0.0001240294,0.00002839008,0.8239305,0.00002481965,0.1670209,0.004524836,0.0001550861],"study_design_scores_gemma":[0.0007112323,0.0001658971,0.005282346,0.00007557601,0.0001309248,0.00001684786,0.00001678433,0.9023576,0.00003775568,0.08441252,0.006046229,0.0007463119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06052842,0.0001192424,0.9356735,0.001252056,0.0004903925,0.0005618671,0.00001980118,0.0006280185,0.0007267104],"genre_scores_gemma":[0.9901376,0.0001147176,0.006789849,0.0004912527,0.0004046446,0.000007783381,0.00009303222,0.00004453084,0.001916551],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9296092,"threshold_uncertainty_score":0.9997135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05029672789779551,"score_gpt":0.1772172203048672,"score_spread":0.1269204924070717,"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."}}