{"id":"W2884013187","doi":"10.1109/tpami.2018.2855738","title":"Scattering Networks for Hybrid Representation Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute; Computer Research Institute of Montréal","funders":"Vlaamse regering; KU Leuven; Natural Sciences and Engineering Research Council of Canada; Fonds Wetenschappelijk Onderzoek","keywords":"Artificial intelligence; Computer science; Scattering; Stability (learning theory); Unsupervised learning; Pattern recognition (psychology); Representation (politics); Convolutional neural network; Feature learning; Competitive learning; Supervised learning; Deep learning; Machine learning; Residual; Artificial neural network; Algorithm; Physics; Optics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001456163,0.0001597812,0.0002016341,0.0002624294,0.0004661392,0.000123913,0.0003445371,0.00003170014,0.00003531023],"category_scores_gemma":[0.000004956769,0.0001542146,0.0001637853,0.0009506092,0.00008532486,0.0002590633,0.000007424347,0.0001876668,0.00001648982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002287631,"about_ca_system_score_gemma":0.000005832521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000112473,"about_ca_topic_score_gemma":0.000235686,"domain_scores_codex":[0.9987163,0.0000497965,0.0002922271,0.0005667292,0.0001352582,0.0002396883],"domain_scores_gemma":[0.9990319,0.0002244763,0.0001160704,0.0004326098,0.0001028141,0.00009213432],"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":[0.000007158514,0.00002863541,0.0002364012,0.000002928284,0.0001079658,7.693613e-7,0.0000744446,0.2759629,0.0003089513,0.00007193341,0.000009431251,0.7231885],"study_design_scores_gemma":[0.00005336812,0.0001090922,0.0002713536,0.000008227836,0.000126763,0.000007313769,0.00001122981,0.9001752,0.09841392,0.0004664401,0.0001991871,0.0001578775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002222799,0.00003602853,0.9967522,0.0004466226,0.000162858,0.0001989666,0.000006763453,0.0001376865,0.00003609119],"genre_scores_gemma":[0.9894911,0.0001624126,0.009594673,0.0003753814,0.00008088232,0.00009537265,0.000007331253,0.00001251481,0.0001803475],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9872683,"threshold_uncertainty_score":0.6288691,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02717808744385188,"score_gpt":0.3037644277812501,"score_spread":0.2765863403373983,"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."}}