{"id":"W2587976075","doi":"10.1109/ssci.2016.7850122","title":"Biasing restricted Boltzmann machines using Gaussian filters to learn invariant visual features","year":2016,"lang":"en","type":"article","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Gaussian filter; Computer science; Gaussian; Pattern recognition (psychology); Unsupervised learning; Preprocessor; Boltzmann machine; Restricted Boltzmann machine; Invariant (physics); Feature extraction; Gaussian blur; Filter (signal processing); Computer vision; Deep learning; Image processing; Mathematics; Image (mathematics); Image restoration","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":[0.0001764581,0.0002074685,0.0002002105,0.0002022105,0.0002560274,0.0003346793,0.0005627956,0.00006637597,0.00007587625],"category_scores_gemma":[0.0002025603,0.0001253086,0.00007698598,0.0005759337,0.0000388294,0.0006718813,0.000274124,0.00008118968,0.00006254767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005826751,"about_ca_system_score_gemma":0.00006539447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004743018,"about_ca_topic_score_gemma":0.0001019114,"domain_scores_codex":[0.9984117,0.0001757632,0.0002221865,0.0005116731,0.0002503131,0.0004283772],"domain_scores_gemma":[0.9990892,0.0001608218,0.0000689055,0.0004003675,0.00007848592,0.0002022238],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006169348,0.00008766211,0.001619308,0.000008157172,0.00008993541,0.00009174371,0.0006322252,0.004921338,0.6432453,0.007517183,0.01924203,0.3224834],"study_design_scores_gemma":[0.002476198,0.0008750107,0.1490253,0.0006111899,0.00007889497,0.0001887131,0.0002352677,0.6574724,0.1652474,0.002190142,0.01886394,0.002735581],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02076584,0.00003625933,0.9707289,0.005249542,0.0004911777,0.0001579531,0.000002384338,0.000158302,0.002409688],"genre_scores_gemma":[0.7772858,0.000006281349,0.2191199,0.001099692,0.0003410143,0.00000409916,7.591528e-7,0.0000175357,0.002124887],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.75652,"threshold_uncertainty_score":0.5109938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02283706878601409,"score_gpt":0.2695525309965295,"score_spread":0.2467154622105154,"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."}}