{"id":"W779272567","doi":"","title":"Understanding deep architectures and the effect of unsupervised pre-training","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Deep learning; Computer science; Generalization; Machine learning; Artificial neural network; Class (philosophy); Unsupervised learning; Set (abstract data type); Process (computing); Variation (astronomy); Deep belief network; Deep neural networks; Restricted Boltzmann machine; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041076,0.001223979,0.0008743198,0.0006141221,0.0006966133,0.002446479,0.002231222,0.002457983,0.002656612],"category_scores_gemma":[0.02826982,0.00112191,0.000844956,0.0006239159,0.003763352,0.01057628,0.002699096,0.004944724,0.0006990763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001555928,"about_ca_system_score_gemma":0.001274162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002507166,"about_ca_topic_score_gemma":0.002342064,"domain_scores_codex":[0.9982705,0.000636522,0.00008152184,0.0004048819,0.0004036105,0.0002028514],"domain_scores_gemma":[0.9890058,0.007175581,0.0008764098,0.001813054,0.0008846749,0.0002443113],"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":[0.000174023,0.0001143107,0.004953643,0.0003922236,0.0001860334,0.0001476839,0.000720231,0.5060268,0.00745775,0.3404028,0.003064966,0.1363597],"study_design_scores_gemma":[0.00002565448,0.0001094399,0.0009615337,0.0001057064,0.00003209479,0.00006589248,0.00007739569,0.5887394,0.004494557,0.4016502,0.003705599,0.00003248253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05413669,0.00241804,0.9272754,0.004895563,0.0002208063,0.00008248977,0.0001215127,0.0007493333,0.01010017],"genre_scores_gemma":[0.7564018,0.003834011,0.2289531,0.001526959,0.0003997798,0.0003142754,0.0003185843,0.0005814674,0.007669922],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0041076,"threshold_uncertainty_score":0.02172327,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03532544690944602,"score_gpt":0.2418295938676839,"score_spread":0.2065041469582379,"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."}}