{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006829538,0.001450893,0.0006989557,0.0007911153,0.0003662505,0.001236718,0.002410527,0.001636192,0.004825827],"category_scores_gemma":[0.001613105,0.0004800475,0.0006781378,0.0009133727,0.00105288,0.002524246,0.002030366,0.001405913,0.001900556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003064,"about_ca_system_score_gemma":0.001299349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006625861,"about_ca_topic_score_gemma":0.01205328,"domain_scores_codex":[0.999612,0.00004851032,0.00002055695,0.0001233786,0.0001384877,0.00005701948],"domain_scores_gemma":[0.9996071,0.00006802032,0.00003582997,0.0001228436,0.0001323963,0.00003381315],"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":[0.000442805,0.0002017846,0.002828885,0.0002003023,0.0001643008,0.0002802624,0.0001123174,0.2840481,0.02565023,0.0211399,0.03391074,0.6310204],"study_design_scores_gemma":[0.00002374584,0.00006773766,0.0003562494,0.00001503612,0.00001167925,0.00009402487,0.00001496085,0.9751257,0.009346932,0.009686487,0.005237984,0.00001946375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04073796,0.0007880404,0.9391642,0.0005484382,0.0003371391,0.00009133184,0.001070012,0.009623508,0.007639457],"genre_scores_gemma":[0.5383879,0.0006267905,0.431704,0.001023648,0.0001312702,0.0002381046,0.005360133,0.001208596,0.02131962],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006625861,"threshold_uncertainty_score":0.01614404,"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."}}