{"id":"W4313437003","doi":"10.1007/s43670-022-00043-5","title":"NESTANets: stable, accurate and efficient neural networks for analysis-sparse inverse problems","year":2022,"lang":"en","type":"article","venue":"Sampling Theory Signal Processing and Data Analysis","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Stability (learning theory); Inverse problem; Artificial neural network; Generalization; Deep learning; Convergence (economics); Key (lock); Artificial intelligence; Inverse; Construct (python library); Mathematical optimization; Algorithm; Theoretical computer science; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001310344,0.0002779548,0.0005232933,0.0005920987,0.0007504922,0.0003146829,0.0004214088,0.00006109195,0.00003639309],"category_scores_gemma":[0.00003240829,0.0002697798,0.0001202324,0.001969296,0.0001074051,0.0002184233,0.0004113132,0.0002821831,1.590556e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003379973,"about_ca_system_score_gemma":0.0000202903,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004548669,"about_ca_topic_score_gemma":0.00004193874,"domain_scores_codex":[0.9981862,0.0001404067,0.0003819753,0.000671197,0.0002185728,0.0004015879],"domain_scores_gemma":[0.9987659,0.0003097345,0.0001465201,0.0005978054,0.00005904418,0.0001210129],"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":[0.00006767398,0.00002438963,0.0004124638,0.00004725419,0.001350103,0.000004058494,0.000210222,0.9793264,0.0002407009,0.00009159208,0.000116595,0.01810852],"study_design_scores_gemma":[0.000186714,0.0000357397,0.0001608205,0.0000179076,0.005886746,0.000006699666,0.0004495812,0.9905753,0.00002421189,0.001727354,0.0005984524,0.0003304458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07557058,0.004826001,0.9186498,0.00002359994,0.00003740812,0.0001976804,0.0002624393,0.0003998334,0.00003263457],"genre_scores_gemma":[0.9926362,0.000103159,0.005854791,0.000112732,0.00005598164,0.00004221322,0.001138963,0.00003762274,0.00001831605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9170656,"threshold_uncertainty_score":0.9999754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05595914766946054,"score_gpt":0.2875084498350968,"score_spread":0.2315493021656362,"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."}}