{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005011628,0.0002143927,0.0003830249,0.00008906432,0.0001518964,0.00009287005,0.0004808639,0.0001025412,0.00002691605],"category_scores_gemma":[0.00009172003,0.000114964,0.0001197685,0.0001395196,0.0001029689,0.00007279741,0.00006560834,0.0001670386,8.299002e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001130894,"about_ca_system_score_gemma":0.00002792502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001113559,"about_ca_topic_score_gemma":0.0002796535,"domain_scores_codex":[0.9988336,0.0003058868,0.0002101611,0.0002960075,0.0001762094,0.0001781646],"domain_scores_gemma":[0.9987628,0.0007177936,0.000148714,0.0003029165,0.00002761459,0.00004017968],"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":[0.0029697,0.00004715438,0.0007763002,0.001160509,0.001711082,0.00001661869,0.1681405,0.007314583,0.003879018,0.2288177,0.0004690156,0.5846977],"study_design_scores_gemma":[0.009549131,0.001881052,0.008383546,0.001069998,0.0008534067,0.00002809757,0.005940802,0.7588009,0.1107276,0.1005571,0.0002062754,0.002002051],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0219275,0.0008041605,0.9460531,0.0000524277,0.0005267481,0.0005261603,9.422822e-7,0.00005308722,0.03005583],"genre_scores_gemma":[0.9936066,0.00003676086,0.005591712,0.00002884014,0.00006335694,0.00001922851,0.000007711865,0.0000129553,0.00063282],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9716791,"threshold_uncertainty_score":0.4688095,"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."}}