{"id":"W2124537004","doi":"10.1016/j.tics.2007.09.004","title":"Learning multiple layers of representation","year":2007,"lang":"en","type":"review","venue":"Trends in Cognitive Sciences","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":1013,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Backpropagation; Representation (politics); Artificial neural network; Computer science; Artificial intelligence; Perception; Generative model; Object (grammar); Generative grammar; Machine learning; Sensory system; Feature learning; Layer (electronics); Pattern recognition (psychology); Psychology; Neuroscience","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":[0.0005440371,0.0007849153,0.0006142816,0.000475524,0.0001491921,0.001147522,0.001524354,0.001089165,0.002869368],"category_scores_gemma":[0.001244168,0.0003248586,0.0004489276,0.0007767477,0.0007126291,0.003681861,0.0009758808,0.001232876,0.001173596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000508072,"about_ca_system_score_gemma":0.0007075442,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007724926,"about_ca_topic_score_gemma":0.001159822,"domain_scores_codex":[0.9998339,0.00002634599,0.00001473936,0.00005513703,0.00005271759,0.00001712956],"domain_scores_gemma":[0.9997081,0.00012833,0.00003361083,0.00006198844,0.00005534607,0.00001262823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002712586,0.00002419734,0.0003093756,0.001018254,0.0001137279,0.00004258934,0.00002419414,0.01124795,0.002523396,0.02853891,0.007828353,0.948302],"study_design_scores_gemma":[0.00004928569,0.0002761166,0.00269949,0.001838574,0.0004658185,0.0017022,0.0001121394,0.1885613,0.03382477,0.355492,0.4148654,0.0001128744],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01656151,0.2585571,0.6827744,0.006714892,0.001561435,0.00008183226,0.0003723538,0.001555872,0.03182061],"genre_scores_gemma":[0.2435365,0.4292297,0.2860208,0.002144058,0.001328894,0.0001730147,0.001367097,0.0001859181,0.03601414],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.002869368,"threshold_uncertainty_score":0.00959897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4044359756793465,"score_gpt":0.5100302918961084,"score_spread":0.1055943162167619,"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."}}