{"id":"W4247067131","doi":"10.1109/cvprw.2009.5206577","title":"Stacks of convolutional Restricted Boltzmann Machines for shift-invariant feature learning","year":2009,"lang":"en","type":"article","venue":"2009 IEEE Conference on Computer Vision and Pattern Recognition","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Restricted Boltzmann machine; Pattern recognition (psychology); Artificial intelligence; Discriminative model; Computer science; Feature extraction; Boltzmann machine; Feature learning; Classifier (UML); Convolutional neural network; Invariant (physics); Feature (linguistics); Cognitive neuroscience of visual object recognition; Deep learning; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001156172,0.0002139346,0.0002396946,0.0001540688,0.0001963524,0.0001198824,0.0002978788,0.0001154229,0.00001257722],"category_scores_gemma":[0.00001425023,0.0001907942,0.00006924074,0.0002397851,0.00004040972,0.0003065351,0.0000453413,0.0002604705,0.00001586341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001785887,"about_ca_system_score_gemma":0.00003430446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004199102,"about_ca_topic_score_gemma":0.000003948332,"domain_scores_codex":[0.9986329,0.00009902993,0.0002893768,0.0005135447,0.0002220324,0.0002431101],"domain_scores_gemma":[0.9989387,0.0002322276,0.0002323736,0.0002478207,0.0002389706,0.0001098502],"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":[0.00005227057,0.0001336181,0.00008899242,0.00002030044,0.000009894193,0.00000455816,0.00009976291,0.0004061043,0.002336621,0.005800477,0.002201884,0.9888455],"study_design_scores_gemma":[0.001256724,0.001843646,0.03125564,0.0003047866,0.00001459614,0.000024081,0.00000415945,0.925451,0.001192041,0.03695573,0.001301895,0.0003957281],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03771712,0.00005090375,0.9584457,0.00278058,0.0002620968,0.0004139507,0.00005187689,0.0001352285,0.0001425766],"genre_scores_gemma":[0.9499131,0.00009287649,0.04850608,0.001012035,0.0002054527,0.00002548334,0.0001651518,0.000009714493,0.00007006447],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9884498,"threshold_uncertainty_score":0.7780362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03690989556709472,"score_gpt":0.291895007643856,"score_spread":0.2549851120767612,"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."}}