{"id":"W3101466225","doi":"","title":"Recurrent neural networks learn robust representations by dynamically balancing compression and expansion","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Curse of dimensionality; Computer science; Recurrent neural network; Stochastic gradient descent; Dimensionality reduction; Artificial intelligence; Generalization; Artificial neural network; Gradient descent; Task (project management); Chaotic; Dynamical systems theory; Machine learning; 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":[0.0007657125,0.0005358931,0.0006783268,0.0003533738,0.000215949,0.0007209216,0.0007164788,0.0006680691,0.000854969],"category_scores_gemma":[0.00484534,0.0004907392,0.0004174041,0.000260241,0.000839434,0.001827775,0.000942005,0.0008461577,0.0002647137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005993642,"about_ca_system_score_gemma":0.0003687782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001489368,"about_ca_topic_score_gemma":0.00175937,"domain_scores_codex":[0.9997699,0.00007254574,0.00001456824,0.0000643025,0.00004031868,0.00003845577],"domain_scores_gemma":[0.9988607,0.0005169174,0.0002604577,0.0001792476,0.0001185744,0.00006405999],"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":[0.00007326792,0.00004259877,0.001363338,0.0000484197,0.00005903886,0.00008644127,0.00009083224,0.9360858,0.01411909,0.01815378,0.0009226701,0.02895476],"study_design_scores_gemma":[0.000002669985,0.00001055525,0.0001069215,0.000002090378,0.000002618054,0.000006243365,0.000003478918,0.9948971,0.000496448,0.004400612,0.00006859268,0.000002657112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4577262,0.0004257557,0.5361594,0.0008047119,0.00006051817,0.00004252259,0.000110146,0.0008898252,0.003781068],"genre_scores_gemma":[0.9801077,0.0001040289,0.01838521,0.00006673237,0.00002664349,0.00003465508,0.00008133555,0.00006375759,0.001129953],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001489368,"threshold_uncertainty_score":0.004348755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02942621118811315,"score_gpt":0.2733511511008031,"score_spread":0.24392493991269,"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."}}