{"id":"W2141122175","doi":"10.1109/tpami.2012.273","title":"Scaling Up Spike-and-Slab Models for Unsupervised Feature Learning","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal","funders":"Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Computer science; Inference; Artificial intelligence; Pattern recognition (psychology); Cognitive neuroscience of visual object recognition; Scaling; Spike (software development); Feature (linguistics); Boltzmann machine; Deep learning; Feature extraction; Algorithm; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002022118,0.0002260757,0.0003208963,0.0002699709,0.0003906475,0.0003372679,0.0002763212,0.000077438,0.00007527521],"category_scores_gemma":[0.000007357736,0.0001862187,0.0002279304,0.0005383154,0.00005052186,0.0005155797,0.000007891636,0.0002488146,0.00001026924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001550417,"about_ca_system_score_gemma":0.00001097901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009362322,"about_ca_topic_score_gemma":0.0001983168,"domain_scores_codex":[0.9986852,0.00008954843,0.0002477916,0.0005490069,0.0001639069,0.0002645608],"domain_scores_gemma":[0.9991444,0.0002307321,0.00007419456,0.0002857457,0.0001293163,0.0001356039],"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":[0.000004393201,0.00002582573,0.00006871294,0.00000938267,0.0002220377,5.613233e-7,0.0003432845,0.3087415,0.0004894818,0.00004771262,0.00001573,0.6900314],"study_design_scores_gemma":[0.00009753473,0.00006656814,0.0001739008,0.000016221,0.0002282124,0.000002728797,0.00008311318,0.9583619,0.04000819,0.0006726849,0.00007679294,0.0002121423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002546292,0.0002243032,0.995782,0.0009497844,0.000165179,0.0002246842,0.00001092681,0.00006090414,0.00003592374],"genre_scores_gemma":[0.9849686,0.0004502659,0.0135033,0.0003701635,0.00003329294,0.00005906058,0.000003997087,0.00001257245,0.0005987589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9824223,"threshold_uncertainty_score":0.7593779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02208093465437513,"score_gpt":0.2480281724877311,"score_spread":0.225947237833356,"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."}}