{"id":"W3087731662","doi":"10.1101/471987","title":"Predictive learning as a network mechanism for extracting low-dimensional latent space representations","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; University of Oregon; Fonds de recherche du Québec – Nature et technologies; University of Washington; DeepMind; Harvard University; National Science Foundation","keywords":"Artificial intelligence; Computer science; Artificial neural network; Latent variable; Curse of dimensionality; Latent variable model; Machine learning; Recurrent neural network; Task (project management); Focus (optics); Space (punctuation); Sequence learning","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001377166,0.00054283,0.000484543,0.000643982,0.0003614994,0.001364264,0.001353676,0.0008462081,0.001989153],"category_scores_gemma":[0.005734378,0.0004584051,0.0006941679,0.0005754272,0.001741109,0.003624452,0.001320442,0.001685798,0.0002549349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008246947,"about_ca_system_score_gemma":0.0004995543,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001449258,"about_ca_topic_score_gemma":0.00138264,"domain_scores_codex":[0.999616,0.0001387461,0.00002282008,0.0001044513,0.00008200626,0.00003592661],"domain_scores_gemma":[0.997995,0.00108827,0.0003463198,0.0003821166,0.0001280821,0.00006021368],"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":[0.0001203982,0.00007340573,0.001848795,0.0001877595,0.0001107496,0.0002017839,0.0002978212,0.4960756,0.03141907,0.4207492,0.001307964,0.04760741],"study_design_scores_gemma":[0.00000640298,0.00001535492,0.0003239421,0.00000813628,0.000006616925,0.00002267249,0.00001086687,0.908783,0.002142607,0.08836791,0.0003031782,0.00000931246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0420091,0.0001731761,0.955251,0.0004914911,0.00003255742,0.0000230805,0.0001048136,0.0003450934,0.001569725],"genre_scores_gemma":[0.8455117,0.0005304134,0.1503594,0.000166918,0.00007592601,0.0001303371,0.0002495075,0.0001160087,0.002859813],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001989153,"threshold_uncertainty_score":0.007283211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02281189902047354,"score_gpt":0.2502228714210581,"score_spread":0.2274109724005846,"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."}}